Do LLMs Understand Limit Order Book Dynamics?
arXiv:2608.23706v1 Announce Type: new Abstract: A large language model (LLM) trained on synthetic limit order book (LOB) data achieves near perfect s
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
arXiv:2608.23740v1 Announce Type: new Abstract: Concurrent multi-agent coding promises division of labor across modules, robustness through redundanc
Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware
arXiv:2608.23807v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (A
Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search
arXiv:2608.23811v1 Announce Type: new Abstract: Automated fact-checking is essential for ensuring the reliability of public health information, yet t
A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification
arXiv:2608.23817v1 Announce Type: new Abstract: SHAP and LIME are now standard tools for interpreting black-box predictions, yet their outputs can va
Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention
arXiv:2608.23834v1 Announce Type: new Abstract: The key-value (KV) cache is a primary capacity and bandwidth bottleneck in long-context LLM serving.
SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models
arXiv:2608.23837v1 Announce Type: new Abstract: Large language models (LLMs) are known to exhibit social sycophancy, often validating or agreeing wit
Exploit More, Explore Smarter for Budget-Constrained Agentic Search
arXiv:2608.23848v1 Announce Type: new Abstract: Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evalu
In-Context Inpainting for Time Series Forecasting
arXiv:2608.23855v1 Announce Type: new Abstract: We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting t
Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications
arXiv:2608.23870v1 Announce Type: new Abstract: When it comes to safety policies for generative AI, one size does not fit all. Each organization and
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
arXiv:2608.23873v1 Announce Type: new Abstract: Everything a language model sees is tokens. The serving stack knows what each span is -- user input,
AI Finds A Way
arXiv:2608.23875v2 Announce Type: new Abstract: Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprisin
Provenance Guided Incremental Learning Under Evolving Concept Definitions
arXiv:2608.23893v1 Announce Type: new Abstract: Learning systems deployed over long periods must adapt not only to statistical changes in incoming da
BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification
arXiv:2608.23898v1 Announce Type: new Abstract: We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification
Quantifying System-Level Harms from AI Adoption in Complex Sociotechnical Systems
arXiv:2608.23906v1 Announce Type: new Abstract: Artificial Intelligence (AI) is increasingly integrated into complex sociotechnical systems, includin
Retrieval-augmented generation vs. deterministic tax computation in multi-agent financial advisory: A 2x2 factorial experiment
arXiv:2608.23908v1 Announce Type: new Abstract: Tax-loss harvesting demonstrates consistent benefits to long-term portfolio growth; yet implementing
PROOF-Gen: From Optimized Data to Better Distillation
arXiv:2608.23911v1 Announce Type: new Abstract: Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling t
MARS: Multi-Specialist LLM Relay System for Competitive Programming
arXiv:2608.23918v1 Announce Type: new Abstract: Large Language Models excel at code generation, yet competitive programming exposes a persistent fail
Data Mixing as Mixture Experiment: Response Surface Methodology and Optimal Design for Large Language Model Pretraining
arXiv:2608.23922v1 Announce Type: new Abstract: Data mixing is a central design problem in large language model pretraining: given a fixed token budg
Evolutionary Recurrent Decision Model in Developing Adaptive and Maladaptive Behaviors
arXiv:2608.23932v1 Announce Type: new Abstract: This study introduces the evolutionarily recurrent decision model (ERDM), a computational reinforceme
More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight
arXiv:2608.23941v1 Announce Type: new Abstract: Pre-execution oversight is core to trusted monitoring in AI control: a fallible LLM monitor vets plan
Recursive Agentic Reasoning
arXiv:2608.23956v1 Announce Type: new Abstract: Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are of
More GPUs or a Smaller Cache? Tensor Parallelism versus KV Compression for Memory-Bound LLM Serving
arXiv:2608.23962v1 Announce Type: new Abstract: When an LLM serving deployment runs out of KVcache room, there are two well-established ways out. Ten
Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design
arXiv:2608.23970v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in understanding and interpre
When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs
arXiv:2608.23978v1 Announce Type: new Abstract: Visual grounding is typically evaluated as a one-shot mapping from an informative referring expressio
Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling
arXiv:2608.23979v1 Announce Type: new Abstract: In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses whic
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
arXiv:2608.23982v1 Announce Type: new Abstract: Scientific reasoning requires language models to retrieve specialized knowledge and incorporate it re
Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction
arXiv:2608.24001v2 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for future prediction, motivating the use of multi
Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing
arXiv:2608.24005v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to assess students' dynamic knowledge states from their learning historie
Reflection with Action-Induced Visual Differences for Desktop GUI Agents
arXiv:2608.24015v1 Announce Type: new Abstract: The Planner-Operator-Reflector (POR) framework is widely used in GUI agents to maintain objective ali
Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding
arXiv:2608.24024v1 Announce Type: new Abstract: Confidence-based voting aggregates parallel LLM rollouts by weighting each with internal signals such
Relative Time Intervals Representation for Word-level Timestamping with Masked Training
arXiv:2608.24041v1 Announce Type: new Abstract: Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, thei
Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment
arXiv:2608.24046v1 Announce Type: new Abstract: When an AI algorithm makes decisions that affect more than one person, aligning it becomes a problem
Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems
arXiv:2608.24069v1 Announce Type: new Abstract: LLM-based multi-agent trading systems, in which specialized agents collaborate through structured com
Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LLM Compression
arXiv:2608.24070v1 Announce Type: new Abstract: Prohibitive computational and environmental costs impede the scalable deployment of Large Language Mo
AgentWorld: Personality-Aware Reliability Evaluation for Agentic Information Retrieval
arXiv:2608.24076v2 Announce Type: new Abstract: Evaluation of agentic information retrieval remains limited to scripted interactions with uniform use
EMRB: A Multi-Level Benchmark for Evaluating LLM Reasoning over Raw Electromagnetic Signals
arXiv:2608.24086v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as code agents for scientific and engineering anal
Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments
arXiv:2608.24099v1 Announce Type: new Abstract: GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-up
ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
arXiv:2608.24103v1 Announce Type: new Abstract: Commercial design platforms increasingly edit documents through large language model (LLM) agents, bu
Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing
arXiv:2608.24112v1 Announce Type: new Abstract: Modern text-to-image (T2I) models often have similar total scores but different strengths, making pra
AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic RL
arXiv:2608.24114v1 Announce Type: new Abstract: Training multi-turn LLM agents with reinforcement learning typically relies on trajectory-level rewar
Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping
arXiv:2608.24135v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has emerged as a pivotal technique for enhancin
OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses
arXiv:2608.24160v1 Announce Type: new Abstract: Multimodal understanding models that can jointly judge text-to-image (T2I), text-to-video (T2V) and t
Task-Adaptive Rubrics for GUI Reward Modeling
arXiv:2608.24174v1 Announce Type: new Abstract: Recent studies on GUI agents have increasingly focused on outcome reward modeling, which assigns outc
Paritok-4B: Intent-Conditioned Context Compression for Coding Agents
arXiv:2608.24188v1 Announce Type: new Abstract: Coding agents re-send large file reads and tool outputs to a frontier LLM every turn, and this contex
Preference Data Selection for Mitigating the Alignment Tax in Large Language Models
arXiv:2608.24192v1 Announce Type: new Abstract: Aligning large language models to human preferences is crucial for real-world deployment but frequent
MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
arXiv:2608.24214v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue sear
Constraint-Guided Enterprise Data Mapping with Large Language Models
arXiv:2608.24218v1 Announce Type: new Abstract: Enterprise entity alignment must handle semi-structured records, implicit attributes, and unit or gra
Evaluating Multiple LLM Generations with Validated Task Coverage
arXiv:2608.24228v1 Announce Type: new Abstract: Many LLM applications are most useful when they provide several candidate outputs for comparison, val
TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models
arXiv:2608.24232v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) generate intermediate reasoning traces that may contain unsafe content,
STRIVE: Multi-Agent Structured Temporal Reasoning with Integrated Verification for Longitudinal Radiology Report Generation
arXiv:2608.24237v1 Announce Type: new Abstract: Longitudinal radiology report generation (LRRG) requires identifying both current findings and their
SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction
arXiv:2608.24252v1 Announce Type: new Abstract: LLM agents can generate paper reproduction code, yet often produce scientifically unfaithful implemen
Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally Grounded Tasks
arXiv:2608.24258v1 Announce Type: new Abstract: AI systems are increasingly evaluated for legally accountable settings, where correct outputs must al
Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing
arXiv:2608.24263v1 Announce Type: new Abstract: Change data synthesis provides a cost-effective solution for expanding training data and improving th
Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding
arXiv:2608.24273v2 Announce Type: new Abstract: Continual knowledge graph embedding updates entity and relation representations as a graph grows. Exi
Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling
arXiv:2608.24274v1 Announce Type: new Abstract: A sustainable diet represents a multi-dimensional synergy among four essential pillars: nutrition ade
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
arXiv:2608.24275v1 Announce Type: new Abstract: Safeguarding language model agents requires assessing complete execution trajectories under context-d
ReproAgent: Contract-Guided Paper-to-Code Reproduction
arXiv:2608.24291v1 Announce Type: new Abstract: Paper-to-code reproduction asks scientific AI agents to turn research papers into executable reposito
VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
arXiv:2608.24302v1 Announce Type: new Abstract: Long-video understanding depends critically on how a limited model context is constructed from a much
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
arXiv:2608.24310v1 Announce Type: new Abstract: Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD)
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
arXiv:2608.24314v1 Announce Type: new Abstract: Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture b
Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control
arXiv:2608.24319v1 Announce Type: new Abstract: An intelligent system does not merely reason: it governs its own reasoning - how much to compute, whe
SonarLLM: A Native Sonar--Optical Multimodal Large Language Model for Underwater Perception
arXiv:2608.24325v1 Announce Type: new Abstract: Reliable underwater perception requires complementary sensing under variable visibility. Optical came
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
arXiv:2608.24338v1 Announce Type: new Abstract: Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, y
The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
arXiv:2608.24358v1 Announce Type: new Abstract: Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. A
Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems
arXiv:2608.24361v1 Announce Type: new Abstract: Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be c
From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use
arXiv:2608.24368v1 Announce Type: new Abstract: Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that eac
Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs
arXiv:2608.24369v1 Announce Type: new Abstract: While large language models (LLMs) possess vast zero-shot procedural knowledge, their tendency to pro
ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
arXiv:2608.24411v1 Announce Type: new Abstract: The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential natur
A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation
arXiv:2608.24419v1 Announce Type: new Abstract: LLM-as-a-judge evaluation is usually assessed by agreement and robustness to surface perturbations, b
Partial Identification under Causal Orders by Linear Programming
arXiv:2608.24427v1 Announce Type: new Abstract: Non-parametric (partial) identification of counterfactual queries typically relies on a fully specifi
A Behavior-Guided Online Probabilistic Forecasting Method for Electric vehicle Charging Loads
arXiv:2608.24441v1 Announce Type: new Abstract: Electric vehicle (EV) charging loads exhibit strong behavioral heterogeneity and temporal variability
Mahalanobis-Based Multi-Head Attention for Complex State Propagation
arXiv:2608.24462v1 Announce Type: new Abstract: In this paper, we propose \textbf{Mahalanobis-Based Multi-Head Attention} (MHA-CSP), a novel attentio
HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning
arXiv:2608.24467v1 Announce Type: new Abstract: Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding,
Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling
arXiv:2608.24470v1 Announce Type: new Abstract: Heterogeneous agile Earth observation satellite (AEOS) scheduling requires task selection, satellite
Implicit Q-learning-bootstrapped ant colony optimization for maritime moving-target observation scheduling with agile satellites
arXiv:2608.24471v1 Announce Type: new Abstract: Maritime moving-target observation scheduling with agile Earth observation satellites is a dynamic, s
PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents
arXiv:2608.24509v1 Announce Type: new Abstract: LLM agents increasingly solve tasks by invoking multiple tools, where parallel execution is essential
Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models
arXiv:2608.24534v1 Announce Type: new Abstract: Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. W
Discovering Adaptive Transmission Programs for Collective Innovation
arXiv:2608.24545v1 Announce Type: new Abstract: Human collective intelligence depends on transmission processes: who shares what with whom, how, and
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
arXiv:2608.24569v1 Announce Type: new Abstract: Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflo
EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents
arXiv:2608.24570v1 Announce Type: new Abstract: Clinical diagnosis is an active evidence-seeking process in which clinicians acquire evidence, update
Joint Optimization of Tool Creation and Use for Large Language Model Agents
arXiv:2608.24571v1 Announce Type: new Abstract: Tool-augmented language models are bounded by the APIs humans bothered to write; existing tool-creati
PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos
arXiv:2608.24574v1 Announce Type: new Abstract: Video multimodal large language models support language guided video segmentation, but they often sho
Pivot-and-Station Multi-Agent Path Finding: Solvability, Complexity, and Algorithms
arXiv:2608.24585v1 Announce Type: new Abstract: Automated high-density storage systems (warehouses, robotic parking, plant logistics, etc.) require f
Causal Modelling of Support Interventions for Student Competency Assessment
arXiv:2608.24632v1 Announce Type: new Abstract: Accurate assessment of student competencies is essential for enabling educators to identify individua
Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning
arXiv:2608.24658v1 Announce Type: new Abstract: Scaling test-time reasoning has substantially improved the problem-solving ability of large language
The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models
arXiv:2608.24662v2 Announce Type: new Abstract: Evaluations of generative language models frequently interpret observable behavioral traits, such as
Confident at the moment of action: belief miscalibration in LLM play under hidden information
arXiv:2608.24691v1 Announce Type: new Abstract: Agentic systems increasingly gate actions on a model's own stated confidence, which assumes confidenc
Lifted Model Construction under Approximate Commutativity
arXiv:2608.24713v1 Announce Type: new Abstract: Lifted inference algorithms enable scalable probabilistic inference even for large object domains by
Meta$^n$: Recursive Self-Improvement through Emergent Depth
arXiv:2608.24735v1 Announce Type: new Abstract: Self-improving LLM agents refine answers, not the process that produces those answers. Systems that a
RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
arXiv:2608.24758v1 Announce Type: new Abstract: Discovering stable neuron behavior across entire domains remains a challenge in mechanistic interpret
Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
arXiv:2608.24764v1 Announce Type: new Abstract: Large language model agents are moving beyond conventional retrieval-augmented generation toward dire
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
arXiv:2608.24777v1 Announce Type: new Abstract: LLM-based agents can interact with external environments through tool invocation, but this capability
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
arXiv:2608.24790v1 Announce Type: new Abstract: Clinicians read chain-of-thought (CoT) rationales as evidence of medical reasoning, but whether the v
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
arXiv:2608.24794v1 Announce Type: new Abstract: Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neithe
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
arXiv:2608.24804v1 Announce Type: new Abstract: We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping m
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core
arXiv:2608.24810v1 Announce Type: new Abstract: Recent work has applied Mamba style state space models (SSMs) to video anomaly detection, yet existin
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA
arXiv:2608.24824v1 Announce Type: new Abstract: Large language models are increasingly used for knowledge graph question answering (KGQA), but can fa
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments
arXiv:2608.24825v1 Announce Type: new Abstract: The rapid expansion of large-scale assessments and the growing adoption of automatic item generation
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs
arXiv:2608.24846v1 Announce Type: new Abstract: Real-world data for knowledge graph question answering is often distributed across different organiza
SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
arXiv:2608.24870v1 Announce Type: new Abstract: Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
arXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure
Progressively Learning Heterogeneous Skills in a Unified Latent Space
arXiv:2608.23258v1 Announce Type: cross Abstract: We propose HetSkills, a novel framework designed to progressively learn heterogeneous skills within
A Human-Factors Guided Cognitive Model of Visuospatial Complexity in Embodied Active Vision
arXiv:2608.23572v1 Announce Type: cross Abstract: We propose a novel framework for the analysis of multimodal data -- encompassing visual, auditory,
Fidelity Preference, Not Demographic Preference: A Pixel-Level Attribute-Sensitivity Audit of Image Aesthetic/Preference Scorers
arXiv:2608.23593v1 Announce Type: cross Abstract: Text-to-image systems use learned aesthetic scorers to filter training data and guide generation, b
REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, gener
Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal
arXiv:2608.23616v2 Announce Type: cross Abstract: An AI agent's rebuild is only as good as the process that produced it. Prior work found that once a
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
arXiv:2608.23619v1 Announce Type: cross Abstract: Legacy software repositories embed decades of domain knowledge in undocumented code, making underst
When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs
arXiv:2608.23623v1 Announce Type: cross Abstract: Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify
Macro-Operator Generation and Predicate Selection for TAMP Operator Learning
arXiv:2608.23629v1 Announce Type: cross Abstract: Creating symbolic operators by hand is one of the main bottlenecks in deploying Task and Motion Pla
ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them
Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail
arXiv:2608.23651v1 Announce Type: cross Abstract: Agent harnesses record a failed tool call and its error message in the transcript and ask the model
Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
arXiv:2608.23653v1 Announce Type: cross Abstract: AI agents are increasingly used for simulation-driven engineering. Physical system modeling present
Elastic KV Cache for LLM Serving:A Working Reclamation Mechanism, and Why Chunked Prefill Already Closes the Gap
arXiv:2608.23658v1 Announce Type: cross Abstract: An LLM serving engine sizes its key-value (KV) cache once, at startup, permanently setting aside a
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
arXiv:2608.23660v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to provide prior causal knowledge for structural
Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Model
arXiv:2608.23663v2 Announce Type: cross Abstract: Aligning deployed language models requires knowing when their outputs can be trusted, yet on-device
The Limits of Automatic Evaluation of Creativity in Large Language Models
arXiv:2608.23705v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly capable of generating text that challenges human perf
Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it
arXiv:2608.23752v1 Announce Type: cross Abstract: The growing size of Convolutional Neural Networks has led to increasingly large and costly models.
EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$
arXiv:2608.23758v1 Announce Type: cross Abstract: Recent large audio language models (LALMs) have achieved impressive progress in audio understanding
TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
arXiv:2608.23763v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model
What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development
arXiv:2608.23766v1 Announce Type: cross Abstract: Between AI-assisted item generation and expert review sits a computational evaluator whose decision
Disentangled Skill Representations for Predictive Human Modeling
arXiv:2608.23776v1 Announce Type: cross Abstract: Understanding human skill is important for AI systems that collaborate with, coach, or assist peopl
When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk
arXiv:2608.23780v1 Announce Type: cross Abstract: LLMs are being used increasingly to measure aspects of student discourse (e.g. talk moves, collabor
EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis
arXiv:2608.23791v1 Announce Type: cross Abstract: Psychological research on emotion dynamics has established that human affect is a continuous, evolv
Restoring Without Forgetting: Continual Learning Across Image Degradations
arXiv:2608.23799v1 Announce Type: cross Abstract: Recent progress in image restoration has converged on all-in-one architectures that jointly handle
LUCAID: Agentic Multimodal AI for Lung Cancer Precision Pathology
arXiv:2608.23803v1 Announce Type: cross Abstract: Lung cancer tissue diagnostics is complex, as therapy decisions in precision oncology rely on the i
Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
arXiv:2608.23809v1 Announce Type: cross Abstract: Multilingual language models can solve the same mathematical problem in different languages, but it
Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring
arXiv:2608.23814v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate strong capabilities in automated essay scoring (AES), but
Place, Slice and Schedule: Hierarchical O-RAN Control of a Tethered mmWave UAV-gNB
arXiv:2608.23824v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV)-mounted 5G New Radio base stations (gNBs) can augment terrestrial net
Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation
arXiv:2608.23836v1 Announce Type: cross Abstract: Accurate interpretation of volumetric CT requires efficient navigation of 3D image volumes and atte
Infant Care Video Dataset for Classification of Interventions Using Transformers
arXiv:2608.23838v1 Announce Type: cross Abstract: Healthcare documentation in the neonatal intensive care unit (NICU) presents significant challenges
Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
arXiv:2608.23839v1 Announce Type: cross Abstract: Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliab
ShardMeter: Sharded and Geo-Distributed Training Without the Guesswork
arXiv:2608.23840v1 Announce Type: cross Abstract: Training large-scale AI models often outgrows a single data center, demanding sharded, multi-cluste
Automated Synthesis of Cloud Emulators
arXiv:2608.23842v1 Announce Type: cross Abstract: DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure m
Coronavirus Optimization Algorithm: A Success-History Adaptive Evolutionary Framework with Archive-Assisted Search and Stagnation Recovery for Global Optimization
arXiv:2608.23847v1 Announce Type: cross Abstract: This paper proposes the Coronavirus Optimization Algorithm (COA), a SARS-CoV-2-inspired success-his
Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)
arXiv:2608.23858v1 Announce Type: cross Abstract: The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven
Revelation Control
arXiv:2608.23860v1 Announce Type: cross Abstract: Revelation Control is the problem of choosing priced interventions that reveal hidden state only in
A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization
arXiv:2608.23885v1 Announce Type: cross Abstract: Real-time optimization (RTO) relies on process models to locate economically optimal operating cond
A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource
arXiv:2608.23892v1 Announce Type: cross Abstract: This article presents the abridged core of \emph{A Mathematical Theory of Interpretation} (MTI), wh
Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory
arXiv:2608.23895v1 Announce Type: cross Abstract: Kohn--Sham density functional theory (DFT) underpins electronic-structure simulations, but repeated
Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs
arXiv:2608.23897v1 Announce Type: cross Abstract: When a code generating language model fabricates a Python package name, an adversary who has pre-re
RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding
arXiv:2608.23928v1 Announce Type: cross Abstract: Surgical spatio-temporal grounding (STG) requires locating, at each video time specified by a proce
QML for Quantum Sensing under Measurement-Induced Information Loss
arXiv:2608.23934v1 Announce Type: cross Abstract: Nitrogen-vacancy (NV) centers in diamond can serve as highly sensitive solid-state quantum sensors
Luce: Relightable Gaussians for 3D Asset Generation
arXiv:2608.23943v1 Announce Type: cross Abstract: High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and a
STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning
arXiv:2608.23952v1 Announce Type: cross Abstract: Federated video anomaly detection trains model collaboratively without sharing raw surveillance foo
The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses
arXiv:2608.23953v1 Announce Type: cross Abstract: An agent harness is what turns a language model into an autonomous agent: the surrounding code that
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
arXiv:2608.23959v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of atta
Evaluating Language Models on Cross-Language Code Functional Equivalence
arXiv:2608.23961v1 Announce Type: cross Abstract: Background: Large Language Models (LLMs) have demonstrated strong performance across a variety of c
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
arXiv:2608.23965v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding
The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem
arXiv:2608.23986v1 Announce Type: cross Abstract: Large language model providers are compute constrained, and their universal response to congestion
Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information bey
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning
WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents
arXiv:2608.24017v1 Announce Type: cross Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
arXiv:2608.24020v1 Announce Type: cross Abstract: Generating executable parametric CAD code from dimension-annotated orthographic drawings is a chall
What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions
arXiv:2608.24022v1 Announce Type: cross Abstract: LLM agents integrated with external resources gain complex task capabilities, yet the unified natur
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning
arXiv:2608.24033v1 Announce Type: cross Abstract: Time series classification underpins applications in healthcare, sensing, and industrial monitoring
Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
arXiv:2608.24039v1 Announce Type: cross Abstract: Manufacturing process planning transforms heterogeneous design information into coherent manufactur
Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models
arXiv:2608.24042v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models pretrained on large-scale robot datasets provide a strong
Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding
arXiv:2608.24048v1 Announce Type: cross Abstract: While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific qu
VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference
arXiv:2608.24063v1 Announce Type: cross Abstract: While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning
Mechanistic Circuit Identification for Controllable Data Generation
arXiv:2608.24065v1 Announce Type: cross Abstract: While recent advances in data synthesis aim to curate high-quality datasets, most generation pipeli
ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal
arXiv:2608.24073v1 Announce Type: cross Abstract: Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applicat
When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs
arXiv:2608.24080v1 Announce Type: cross Abstract: In psychological counseling, effective support is not always delivered through long, information-ri
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
arXiv:2608.24082v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effective
Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents
arXiv:2608.24087v1 Announce Type: cross Abstract: Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or aft
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes
arXiv:2608.24107v1 Announce Type: cross Abstract: Material replacement is a common interior-design operation: changing the material of a selected sur
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
arXiv:2608.24113v1 Announce Type: cross Abstract: Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring
PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control
arXiv:2608.24115v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) can integrate long visual histories, reason under partial
TransPhy: Visual In-Context Learning for Physically Grounded Image Editing
arXiv:2608.24119v1 Announce Type: cross Abstract: Visual demonstrations provide a natural interface for specifying image transformations that are dif
Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking
arXiv:2608.24130v1 Announce Type: cross Abstract: Multi-camera 3D perception systems for warehouse scenes are trained largely on synthetic data and e
From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender
arXiv:2608.24132v1 Announce Type: cross Abstract: Product catalogs in fast-moving service businesses are shifting from static, independently priced S
PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Grounding and Affective Alignment
arXiv:2608.24133v1 Announce Type: cross Abstract: People search for urban outdoor places not only by category or function, but also by what activitie
Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection
arXiv:2608.24154v1 Announce Type: cross Abstract: Real-world deployment of traffic surveillance systems is bottlenecked by geographic domain shift, i
LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes
arXiv:2608.24156v1 Announce Type: cross Abstract: Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordi
Preference Optimization for Non-Verbal Vocalization Synthesis
arXiv:2608.24163v1 Announce Type: cross Abstract: Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive T
Tlow: Flow-based Item Tokenizer for Recommendation
arXiv:2608.24176v1 Announce Type: cross Abstract: Item tokenizer encodes semantic embeddings into token IDs to replace the randomly assigned item IDs
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
arXiv:2608.24191v1 Announce Type: cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely abs
Contrastive Branch Policy Optimization
arXiv:2608.24300v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn i
SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling
arXiv:2608.24304v1 Announce Type: cross Abstract: Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-base
Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning
arXiv:2608.24340v1 Announce Type: cross Abstract: The prediction of student engagement from the online tutoring videos is difficult because engagemen
Metadata-Aware Adaptation of a Generative Foundation Model for Conditional CMR Synthesis
arXiv:2608.24342v1 Announce Type: cross Abstract: Synthetic image generation is a promising strategy to address data scarcity and the underrepresenta
FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision
arXiv:2608.24350v1 Announce Type: cross Abstract: To reduce the hallucination risk caused by outcome-driven rewards in large language models trained
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
arXiv:2608.24354v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from t
Markerless Pose Estimation for Resistance Training Technique Assessment
arXiv:2608.24384v1 Announce Type: cross Abstract: Resistance training can be a high risk activity, and safe form is essential to avoiding injury. Lab
Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning
arXiv:2608.24386v1 Announce Type: cross Abstract: Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification
Multilevel Fair Allocation under Additive Preferences
arXiv:2608.24400v1 Announce Type: cross Abstract: We study multilevel fair resource allocation with tree-structured hierarchical relations among agen
Evaluating Deep Multivariate Imputation Models on Wearable Device Data
arXiv:2608.24436v1 Announce Type: cross Abstract: Wearable device data enables continuous health monitoring, but suffers from structured missingness:
Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning
arXiv:2608.24482v1 Announce Type: cross Abstract: Mechanistic Localization bridges mechanistic interpretability and post-training optimization by iso
When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study
arXiv:2608.24492v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) methods are widely used for hallucination detection in large langua
Scalable and Versatile Identification for Hierarchical Structural Causal Models: A New Look at Project STAR
arXiv:2608.24500v1 Announce Type: cross Abstract: The STAR (Student-Teacher Achievement Ratio) experiment (1985, Tennessee, USA) is a landmark hierar
LumiXAI: A Modular Full-Stack Framework for Feature Attribution
arXiv:2608.24524v1 Announce Type: cross Abstract: Feature attribution is a central tool of model interpretability, yet the software through which it
FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment
arXiv:2608.24551v1 Announce Type: cross Abstract: Machine learning models are widely used in financial fraud and credit-risk detection, yet their adv
StrokeGuard: A Multi-Agent Guided System for Prehospital Stroke Assessment
arXiv:2608.24555v1 Announce Type: cross Abstract: Prehospital stroke assessment aims to accurately identify stroke symptoms and make rapid decisions
COCI: Conference Organisers and Content Identifier
arXiv:2608.24559v1 Announce Type: cross Abstract: Despite the critical role of grey literature in scholarly communication, artefacts such as Calls fo
Across the Loss Landscape with Progressive Growth
arXiv:2608.24568v1 Announce Type: cross Abstract: Deep neural networks generalize well despite their highly nonconvex, overparameterized loss landsca
$\texttt{findr}$: Transparent and Fair Credit Risk Decisions through Semi-Structured Regressions
arXiv:2608.24582v1 Announce Type: cross Abstract: Credit risk models increasingly need to combine predictive accuracy with transparent explanations a
Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks
arXiv:2608.24597v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models
A Literate Programming Environment for Human and Machine Agents
arXiv:2608.24644v1 Announce Type: cross Abstract: This paper introduces an environment for constructing literate programs in concert with language-aw
Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems
arXiv:2608.24650v2 Announce Type: cross Abstract: System-level simulation is an essential tool for exploring the rapidly expanding design space of LL
Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration
arXiv:2608.24664v1 Announce Type: cross Abstract: We introduce Maia 200, an advanced AI accelerator delivering high performance-10 145 Tflop/s FP4 an
On-policy Distillation with Verifiable Reward
arXiv:2608.24696v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become
Constrained Hyperparameter Optimization for Streaming Data
arXiv:2608.24712v1 Announce Type: cross Abstract: Optimization of hyperparameters is a critical factor to obtain optimal model performance. While exi
Deep Learning Super Resolution for Satellite Cloud Mask Downscaling
arXiv:2608.24715v1 Announce Type: cross Abstract: A vast amount of optical satellite data is being transmitted to Earth-based servers every day, and
Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity
arXiv:2608.24721v1 Announce Type: cross Abstract: Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active
Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets
arXiv:2608.24727v1 Announce Type: cross Abstract: EEG foundation models pretrained via self-supervised learning promise transferable representations,
Method, Mind, and Morality: How People Make Sense of Artificial Intelligence
arXiv:2608.24748v1 Announce Type: cross Abstract: How can humans make sense of the rapid takeoff of artificial intelligence (AI)? We studied the sens
The RAT: A Unified Bayesian Model for RAG Evaluation
arXiv:2608.24753v1 Announce Type: cross Abstract: Evaluating Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end corr
Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
arXiv:2608.24762v1 Announce Type: cross Abstract: Many disentanglement methods represent generative factors using Euclidean product coordinates, alth
Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks
arXiv:2608.24768v1 Announce Type: cross Abstract: The Bayesian Ideal Observer (IO) establishes the theoretical upper bound on task performance for bi
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
arXiv:2608.24771v1 Announce Type: cross Abstract: Brain stroke, known for its high mortality and incidence rates, poses significant health risks and
Automatic Model Card Generation Using an LLM
arXiv:2608.24807v1 Announce Type: cross Abstract: Model cards are structured documents that summarize key information about machine learning models t
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows
arXiv:2608.24842v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosu
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
arXiv:2608.24845v1 Announce Type: cross Abstract: We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B
Fuzzy Segmentations of a String
arXiv:2201.13427v2 Announce Type: replace Abstract: This article discusses a particular case of the data clustering problem, where it is necessary to
Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives
arXiv:2304.10041v3 Announce Type: replace Abstract: This work investigates formal policy synthesis for continuous-state stochastic dynamic systems su
Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
arXiv:2312.17535v2 Announce Type: replace Abstract: In the past two years, the outstanding performance of ChatGPT in multilingual and multitasking ha
LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis
arXiv:2406.05375v4 Announce Type: replace Abstract: Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex sys
Efficient LLM Collaboration via Planning
arXiv:2506.11578v5 Announce Type: replace Abstract: Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple
Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
arXiv:2507.11482v5 Announce Type: replace Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agent
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
arXiv:2511.02605v3 Announce Type: replace Abstract: Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent
UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
arXiv:2511.08873v4 Announce Type: replace Abstract: Large language models (LLMs) are shifting from answer providers to intelligent tutors in educatio
ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering
arXiv:2512.13979v2 Announce Type: replace Abstract: Large reasoning models achieve strong performance on diverse tasks by producing extended chains o
Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge
arXiv:2601.10485v5 Announce Type: replace Abstract: Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compa
Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
arXiv:2602.02304v3 Announce Type: replace Abstract: Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as s
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
arXiv:2602.09159v2 Announce Type: replace Abstract: Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume c
PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
arXiv:2604.01532v3 Announce Type: replace Abstract: LLM agents are beginning to invoke industrial asset-management tools through the Model Context Pr
Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints
arXiv:2604.01841v4 Announce Type: replace Abstract: Clinical prediction from structured electronic health records (EHRs) is challenging due to high d
ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
arXiv:2604.15994v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reas
Housing Potential Common Data Model and City Digital Twin
arXiv:2605.05535v2 Announce Type: replace Abstract: The evaluation of housing potential requires consideration of a location from multiple perspectiv
Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust
arXiv:2605.10059v3 Announce Type: replace Abstract: Agent-based modeling (ABM) has long been used in economics to study human behavior, and large lan
EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design
arXiv:2605.19743v3 Announce Type: replace Abstract: Engineering-agent systems are proliferating, but differences in tasks, tools, and success criteri
Self-Evolving Scientific Agent Designs Physically-Reasoned Whitebox Fluid Control
arXiv:2606.08405v3 Announce Type: replace Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientifi
Atomic Units of X: The Compression Layer of Intelligence
arXiv:2607.12634v2 Announce Type: replace Abstract: This paper proposes a theoretical and empirical framework for understanding intelligence as a pro
SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents
arXiv:2608.08253v2 Announce Type: replace Abstract: We present SuperLocalMemory 4.0, a governed, local-first memory operating system for AI agents, u
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
arXiv:2608.09696v4 Announce Type: replace Abstract: A primary goal of science is to learn mechanistic or causal world models from data. These model
The Dynamics of Intelligence Explosions
arXiv:2608.14426v2 Announce Type: replace Abstract: AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loo
Auditing an AI-Generated Mathematical Proof: Human Assessment of OpenAI's Quantum Parallel-Repetition Argument
arXiv:2608.14673v2 Announce Type: replace Abstract: We present an independent human assessment of the proof developed in Chapter 6 of OpenAI's Ten Ad
Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
arXiv:2608.16645v3 Announce Type: replace Abstract: Can a language model recover the true research idea of a published paper when given only that pap
ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
arXiv:2608.20009v2 Announce Type: replace Abstract: Understanding object dynamics requires not only predicting future trajectories but also examining
What You Can't See Is What You Learn: Slot-Selective Evidence Masking Favors Compositional Generalization in Shared-Genome Language-Model Societies
arXiv:2608.20054v3 Announce Type: replace Abstract: Multi-module neural systems often expose every module to the full input. We test whether a slot-s
SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing
arXiv:2608.22018v2 Announce Type: replace Abstract: Hate speech research has moved from coarse-grained classification towards structured parsing, whe
GenCoord: Skill-Path Commitments under Private Information
arXiv:2608.22055v2 Announce Type: replace Abstract: Suppose one embodied agent knows what must be built, while its teammate alone knows which transfo
Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models
arXiv:2608.22232v2 Announce Type: replace Abstract: Real-world situation appearances can deviate from their underlying physical states, challenging t
CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents
arXiv:2608.22577v2 Announce Type: replace Abstract: Long-horizon GUI agents can retain complete action histories as compact text, but only a few hist
SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems
arXiv:2608.22979v2 Announce Type: replace Abstract: Deploying high-dimensional multimodal features in industrial recommender systems incurs substanti
MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks
arXiv:2608.23035v2 Announce Type: replace Abstract: As on-device LLM agents evolve into personal copilots, the mobile operating system has become a k
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
arXiv:2608.23283v2 Announce Type: replace Abstract: General-purpose language models can reason and synthesize knowledge, but complex work also requir
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction
arXiv:2608.23397v2 Announce Type: replace Abstract: Interactive clinical agents operate under partial observability, so reliable care depends on reac
Screening Autism Spectrum Disorder in children using Deep Learning Approach : Evaluating the classification model of YOLOv26s by comparing with other models
arXiv:2306.14300v2 Announce Type: replace-cross Abstract: Autism spectrum disorder (ASD) is a developmental condition that presents significant chall
HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA
arXiv:2402.01767v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) significantly improves document-based question answeri
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
arXiv:2407.00500v2 Announce Type: replace-cross Abstract: Recent point-based intrinsic decomposition and inverse rendering methods have advanced the
Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
arXiv:2412.02520v4 Announce Type: replace-cross Abstract: Connected automated vehicles (CAVs) equipped with adaptive cruise control (ACC) create new
Generative AI for Validating Physics Laws
arXiv:2503.17894v3 Announce Type: replace-cross Abstract: We propose generative learner for estimating heterogeneous treatment effects and characteri
Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review
arXiv:2504.18346v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been transformative across many domains. However, halluci
Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric
arXiv:2505.23197v5 Announce Type: replace-cross Abstract: Path planning for autonomous robots faces a fundamental trade-off between path length and o
Quasar: A Programming Language Specialized for LLM Code Actions
arXiv:2506.12202v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often call external tools to solve tasks. One effective strate
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
arXiv:2506.13182v3 Announce Type: replace-cross Abstract: [...] Since then, various APR approaches, especially those leveraging the power of large la
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
arXiv:2506.20073v3 Announce Type: replace-cross Abstract: Spatio-temporal data mining plays a pivotal role in informed decision making across diverse
Can large language models assist choice modelling? Insights into prompting strategies and current models' capabilities
arXiv:2507.21790v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are becoming widely used to support various workflows across d
NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
arXiv:2508.09473v2 Announce Type: replace-cross Abstract: Ensuring robust safety alignment while preserving utility is critical for the reliable depl
An Information-Flow Perspective on Explainability Requirements: Specification and Verification
arXiv:2509.01479v4 Announce Type: replace-cross Abstract: Explainable systems expose information about why certain observed effects are happening to
STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
arXiv:2509.03754v2 Announce Type: replace-cross Abstract: Responding to rising global food security needs, precision agriculture and deep learning-ba
Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
arXiv:2509.15959v2 Announce Type: replace-cross Abstract: Autonomous navigation in maritime domains is accelerating alongside advances in artificial
VGGT-DP: Generalizable Robot Control via Vision Foundation Models
arXiv:2509.18778v2 Announce Type: replace-cross Abstract: Visual imitation learning frameworks allow robots to learn manipulation skills from expert
Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics?
arXiv:2510.14249v2 Announce Type: replace-cross Abstract: Understanding and modeling the relationship between language and sound are essential for ap
Monotone and Separable Set Functions: Characterizations and Neural Models
arXiv:2510.23634v5 Announce Type: replace-cross Abstract: Motivated by applications for set containment problems, we consider the following fundament
CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution
arXiv:2511.01870v3 Announce Type: replace-cross Abstract: Studying the cellular architecture of the human cerebral cortex is essential for understand
Robust Motion Generation using Part-level Reliable Data from Videos
arXiv:2512.12703v2 Announce Type: replace-cross Abstract: Extracting human motion from large-scale web videos offers a scalable solution to the data
Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library
arXiv:2512.16715v3 Announce Type: replace-cross Abstract: In recent years, Predictive Process Mining (PPM) techniques based on artificial neural netw
Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
arXiv:2601.00282v3 Announce Type: replace-cross Abstract: Quantization is widely used to accelerate inference and streamline the deployment of large
Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes
arXiv:2601.07737v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in mainst
Minimal Decision Dynamics and Contextual Probability: A Quantum Tug-of-War Model
arXiv:2601.10034v3 Announce Type: replace-cross Abstract: Decision making often exhibits context dependence that is difficult to accommodate within a
TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning
arXiv:2601.16520v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recogn
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
arXiv:2601.17027v2 Announce Type: replace-cross Abstract: While synthetic data has proven effective for improving scientific reasoning in the text do
Ad Insertion in LLM-Generated Responses
arXiv:2601.19435v2 Announce Type: replace-cross Abstract: Sustainable monetization of large language models (LLMs) remains a critical open challenge.
Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging
arXiv:2602.03702v2 Announce Type: replace-cross Abstract: Large language models are increasingly trained in continual or open-ended settings, where t
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
arXiv:2602.10863v2 Announce Type: replace-cross Abstract: Long-horizon reinforcement learning for information seeking agents remains difficult becaus
PatientHub: A Unified Framework for Patient Simulation
arXiv:2602.11684v2 Announce Type: replace-cross Abstract: As Large Language Models increasingly power role-playing applications, simulating patients
You Can Learn Tokenization End-to-End with Reinforcement Learning
arXiv:2602.13940v3 Announce Type: replace-cross Abstract: Tokenization is a hardcoded compression step which remains in the training pipeline of Larg
VLANeXt: Recipes for Building Strong VLA Models
arXiv:2602.18532v3 Announce Type: replace-cross Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged
ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents
arXiv:2603.00188v3 Announce Type: replace-cross Abstract: Training-free KV cache compression is essential for deploying vision-language GUI agents un
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
arXiv:2603.02041v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are predominantly trained on English-centric data, resulting i
ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
arXiv:2603.10068v2 Announce Type: replace-cross Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and
msData: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models
arXiv:2603.16497v3 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across
Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
arXiv:2603.16654v3 Announce Type: replace-cross Abstract: Evaluating the reasoning abilities of large language models (LLMs) solely from final answer
Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
arXiv:2603.17170v2 Announce Type: replace-cross Abstract: AI agents increasingly execute users' natural-language (NL) tasks by calling Web services,
Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification
arXiv:2603.25507v2 Announce Type: replace-cross Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its pra
Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks
arXiv:2604.14211v2 Announce Type: replace-cross Abstract: This thesis is an exposition of Ollivier-Ricci Curvature of metric spaces as introduced by
Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts
arXiv:2604.16926v3 Announce Type: replace-cross Abstract: Electroencephalography (EEG) foundation models have shown strong potential for learning gen
RA-CMF: Region-Adaptive Conditional MeanFlow for CT Image Reconstruction
arXiv:2605.00901v2 Announce Type: replace-cross Abstract: The use of CT imaging is important for screening, diagnosis, therapy planning, and prognosi
Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
arXiv:2605.02867v3 Announce Type: replace-cross Abstract: Despite significant advances in Reinforcement Learning (RL), model performance remains high
Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
arXiv:2605.06647v3 Announce Type: replace-cross Abstract: Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet mos
Outlier-Robust Diffusion Solvers for Inverse Problems
arXiv:2605.09477v2 Announce Type: replace-cross Abstract: Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently ac
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
arXiv:2605.10426v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end aut
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
arXiv:2605.11048v2 Announce Type: replace-cross Abstract: Existing imitation learning methods enable robots to interact autonomously with the physica
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
arXiv:2605.26958v2 Announce Type: replace-cross Abstract: Reinforcement learning in open-ended long-form generation is challenging because reliable r
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
arXiv:2605.28791v2 Announce Type: replace-cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged in
A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink
arXiv:2606.00930v2 Announce Type: replace-cross Abstract: Mechanistic interpretability routinely reads a probe and labels its top-activating units as
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
arXiv:2606.04120v2 Announce Type: replace-cross Abstract: Conversational agents that serve as lifelong companions must maintain persistent memory acr
When Can One Neuron Fix Repetition Loops in LLMs?
arXiv:2606.13705v2 Announce Type: replace-cross Abstract: The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumerat
TW-LegalBench: Measuring Taiwanese Legal Understanding
arXiv:2606.18699v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet t
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
arXiv:2606.22027v4 Announce Type: replace-cross Abstract: Reinforcement learning for robot manipulation is often bottlenecked by reward design, espec
Co-occurring Associated REtained concepts in Diffusion Unlearning
arXiv:2606.24192v2 Announce Type: replace-cross Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusi
Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop
arXiv:2606.29717v3 Announce Type: replace-cross Abstract: Predicting a material's properties from its structure is a central, fast-advancing problem
A Unified Algebraic Framework for Classification Performance Evaluation
arXiv:2607.04028v2 Announce Type: replace-cross Abstract: We propose a unified algebraic framework for classification performance evaluation covering
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
arXiv:2607.08960v2 Announce Type: replace-cross Abstract: Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode compl
The Caf\'e in Amsterdam: When the Incumbent Becomes the Oracle
arXiv:2607.13393v3 Announce Type: replace-cross Abstract: A field can reformulate its computations freely exactly where its demand is stated independ
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
arXiv:2607.13431v2 Announce Type: replace-cross Abstract: Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternativ
EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology
arXiv:2607.19261v4 Announce Type: replace-cross Abstract: Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, exa
GraphVid: Interactive Graph-Controllable Video Generation
arXiv:2607.21580v2 Announce Type: replace-cross Abstract: Controllable video generation remains challenging due to the difficulty of specifying preci
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
arXiv:2607.24555v2 Announce Type: replace-cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache,
MOSAIC: Masked Outsourcing of Secure AI Computations
arXiv:2607.29221v2 Announce Type: replace-cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a tru
TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
arXiv:2608.01400v2 Announce Type: replace-cross Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and
Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset
arXiv:2608.06165v3 Announce Type: replace-cross Abstract: Existing audio-to-score (A2S) systems primarily focus on classical music, and the applicati
AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization
arXiv:2608.07557v2 Announce Type: replace-cross Abstract: Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reacti
Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol
arXiv:2608.08882v4 Announce Type: replace-cross Abstract: AI tools that help people judge online claims are usually evaluated while the tool is prese
ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning
arXiv:2608.14773v2 Announce Type: replace-cross Abstract: The efficient-KAN literature---covering Chebyshev, wavelet, and radial-basis-function varia
MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation
arXiv:2608.15299v2 Announce Type: replace-cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of
From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation
arXiv:2608.18076v2 Announce Type: replace-cross Abstract: Large-scale image generation has benefited from advances in data scale, quality, rebalancin
Formal Verification of Romanov's Triplet Logic: A Verified Filter for Sliding-window 3-CNF with Application to Structured Formulas
arXiv:2608.18445v3 Announce Type: replace-cross Abstract: We present the first mechanised formalisation of Romanov's Triplet Logic (TLS) in the Rocq
Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
arXiv:2608.19760v2 Announce Type: replace-cross Abstract: Audited against policy-conditional ground truth from executed replay in a single-agent tool
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
arXiv:2608.20539v2 Announce Type: replace-cross Abstract: Digital twin simulations show promise, but current empirical evidence suggests that the app
Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation
arXiv:2608.20804v2 Announce Type: replace-cross Abstract: Temporal Knowledge Graph (TKG) extrapolation seeks to infer future facts from time-varying
Scaling Muon for Diffusion Transformers
arXiv:2608.20818v3 Announce Type: replace-cross Abstract: The matrix-aware optimizer Muon improves large model training by balancing updates across s
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents
arXiv:2608.21114v2 Announce Type: replace-cross Abstract: Visual world-model agents such as DreamerV3 act through a recurrent latent state rather tha
Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds
arXiv:2608.21170v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet recent wor
Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores
arXiv:2608.21829v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation treats the document store as a frozen input, and the offline
DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation
arXiv:2608.22067v3 Announce Type: replace-cross Abstract: World-Action Models (WAMs) build robot control on video-generation backbones, which jointly
SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models
arXiv:2608.22354v2 Announce Type: replace-cross Abstract: Delta-Rule recurrent models maintain a fixed-size state, enabling $O(1)$ inference memory b
Functional compatibility as a determinant of persistent neural learning
arXiv:2608.22462v2 Announce Type: replace-cross Abstract: Neural networks can acquire new capabilities while damaging existing ones, but what determi
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
arXiv:2608.22876v2 Announce Type: replace-cross Abstract: Hybrid sequence models must satisfy prefix invariance: representations at position t must n
Molecular LLM Agents: From Architectural Design to Scientific Autonomy
arXiv:2608.23104v2 Announce Type: replace-cross Abstract: Molecular science represents an important frontier for LLM-based agents. Unlike general age
How Much Regularization Survives Averaging? Update Masking in Federated Learning
arXiv:2608.23286v2 Announce Type: replace-cross Abstract: Federated learning on non-IID data seeks flat minima to generalize across clients, and exis
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
arXiv:2608.23329v2 Announce Type: replace-cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
arXiv:2608.23391v2 Announce Type: replace-cross Abstract: Structured data exists in many forms (tables, knowledge graphs, charts, and time series), a
What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
arXiv:2608.23474v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve strong performance on video and image-sequence benchm
Best Practice Critic Optimization
arXiv:2608.23566v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning methods such as GRPO for large language models avoid tra
Skill Issue: Are Skills Language-Invariant in LLMs?
Large language models access knowledge inconsistently across languages, but to what extent do they differ in their skill sets when interacting with di
Prefix Sliding for efficient test-time scaling
Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer when solving a problem. As models
Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling
The development of 0.1^{circ} global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-reso
LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
We introduce LibriBrain100, a large-scale MEG dataset for speech decoding designed from the ground up for reproducible, standardised evaluation. Libri
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents be
A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
Reliable spatial understanding is an important prerequisite for future medical vision-language systems that aim to support radiological report generat
RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval
Document retrieval increasingly supports high-stakes information access in finance, healthcare, and law. Modern retrieval pipelines vary both in modal
Real-TurnTurk: A Multimodal Turkish Corpus for Turn-Taking Prediction
Turn-taking is a basic organizational feature of human conversation and remains difficult to model in natural, synchronous dialog systems. While exist
Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data
Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reaso
The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, fol
Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios
Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding. However, their ability to follow instructions in this d
FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling
Reliable reward models are essential for text-to-video evaluation and alignment. However, the trade-off between evaluation accuracy and inference effi
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identi
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame predicti
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
Conversational systems, such as duplex speech language models (SLMs), still lack a streaming, accurate, and empathetic memory system as their soul. We
Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation
Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserv
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for
MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization
Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) models integrate perception, langu
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a s
Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) expe
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, o
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool
VGI-BENCH: Probing Visual Intelligence in Video Generation Models
Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable eva
Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments
GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-ups to action misuse, yet existing benchmarks lack
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans
Existing co-speech gesture generation methods are predominantly studied in offline settings, where gestures are synthesized from complete speech segme
D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergen
A Programming Paradigm for Spatiotemporal Composability
Modern software -- from plugin systems to self-evolving agent harnesses -- increasingly requires dynamic composition, yet its formal foundations remai
FrontierChallenge: Evaluating Scientific Workflow Completion
Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated progr
Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each ro
Code World Model: Coding Agent as World Brain
World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be
MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversation
Memory systems for conversational LLMs are conventionally evaluated by direct, fact-seeking questions about prior dialogue (Direct QA): can the model
MARS: Multi-Specialist LLM Relay System for Competitive Programming
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribu
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream state is repeatedly transformed into
Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families purs
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation
Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may injec
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel exploration at the natural granul
Automata from Agent Traces: Failure and Next-Step Prediction
LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runt
GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task
MoTE: Mixture of Task Experts for Multi-Task Video Understanding
Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedur
DREAM Technical Report
Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment inform
Latent Action as Intention Enables Efficient Future Imagination for World Action Models
World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substanti
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,
Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-th
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task da
From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms
Smart glasses are evolving from capture and display accessories into first-person intelligence platforms that connect human perception, persistent con
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from Common
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space
TorchMorph: CUDA-accelerated Morphological Transforms
Morphological transforms are long-standing tools for shape and mask processing, but the de facto reference implementation in the Python ecosystem, i.e