Paper2Code archive

Paper archive page 41

Page 41 of 129. Links match the indexable papers sitemap inventory.

300 canonical paper links on this archive page.

CoDA: Co-Evolution of Data Engines and Action Policies
arxiv-2610.22362 Sparse Blocked context only

Oct 15, 2026
SUPRA-TEX: 3D Generation with Super-Aligned Texture
arxiv-2610.22352 Direct Blocked context only

Oct 15, 2026
Rethinking Routing Exploration in Modern Mixture-of-Experts
arxiv-2610.22353 Sparse Blocked context only

Oct 15, 2026
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
arxiv-2610.22344 Curated Related Blocked context only

Oct 15, 2026
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
arxiv-2610.22328 Sparse Blocked context only

Oct 15, 2026
Training Reasoning Models to Generate Diverse Scientific Ideas
arxiv-2610.22324 Sparse Blocked context only

Oct 15, 2026
Learning to Steer LLM Agents and Multi-Agent Systems
arxiv-2610.22316 Sparse Blocked context only

Oct 15, 2026
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
arxiv-2610.22298 Sparse Blocked context only

Oct 15, 2026
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
arxiv-2610.22293 Sparse Blocked context only

Oct 15, 2026
Improving Environment-Agnostic Coding Agents: The Role of Scaffolding
arxiv-2610.22289 Sparse Blocked context only

Oct 15, 2026
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
arxiv-2610.22276 Sparse Blocked context only

Oct 15, 2026
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
arxiv-2610.22273 Sparse Blocked context only

Oct 15, 2026
X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
arxiv-2610.22269 Sparse Blocked context only

Oct 15, 2026
Language Is a Security Surface for Agent Guards
arxiv-2610.22244 Sparse Blocked context only

Oct 15, 2026
OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
arxiv-2610.22234 Sparse Blocked context only

Oct 15, 2026
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
arxiv-2610.22217 Sparse Blocked context only

Oct 15, 2026
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
arxiv-2610.22195 Sparse Blocked context only

Oct 15, 2026
Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization
arxiv-2610.22127 Sparse Blocked context only

Oct 15, 2026
Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
arxiv-2610.22448 Sparse Blocked context only

Oct 15, 2026
Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning
arxiv-2610.22444 Sparse Blocked context only

Oct 15, 2026
Learning to Think and Explore in 3D World
arxiv-2610.21783 Sparse Blocked context only

Oct 15, 2026
Data World: Scaling Data Environments from Scratch
arxiv-2610.21656 Sparse Blocked context only

Oct 15, 2026
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
arxiv-2610.21601 Sparse Blocked context only

Oct 15, 2026
DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
arxiv-2610.21561 Sparse Blocked context only

Oct 15, 2026
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
arxiv-2610.21463 Sparse Blocked context only

Oct 15, 2026
Can Visual Generation Expand What Unified Multimodal Models Know?
arxiv-2610.21459 Sparse Blocked context only

Oct 15, 2026
CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance
arxiv-2610.21453 Sparse Blocked context only

Oct 15, 2026
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
arxiv-2610.21439 Sparse Blocked context only

Oct 15, 2026
Resisting Harmful Instructions through Training-Free Weight Editing
arxiv-2610.21189 Sparse Blocked context only

Oct 15, 2026
Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
arxiv-2610.21109 Sparse Blocked context only

Oct 15, 2026
Sci$Π$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
arxiv-2610.21082 Sparse Blocked context only

Oct 15, 2026
Amortizing Sequential Experimental Design in Reasoning LLMs
arxiv-2610.20832 Sparse Blocked context only

Oct 14, 2026
When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following
arxiv-2610.20805 Sparse Blocked context only

Oct 14, 2026
SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
arxiv-2610.20609 Sparse Blocked context only

Oct 14, 2026
Latent Compaction with Test-Time Training
arxiv-2610.20582 Sparse Blocked context only

Oct 14, 2026
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
arxiv-2610.20503 Sparse Blocked context only

Oct 14, 2026
Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR
arxiv-2610.20461 Sparse Blocked context only

Oct 14, 2026
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
arxiv-2610.20220 Sparse Blocked context only

Oct 14, 2026
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
arxiv-2610.23987 Sparse Blocked context only

Oct 14, 2026
BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References
arxiv-2610.23986 Sparse Blocked context only

Oct 14, 2026
Generative World Simulation with DAO and JING
arxiv-2610.19726 Sparse Blocked context only

Oct 14, 2026
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
arxiv-2610.19705 Sparse Blocked context only

Oct 14, 2026
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
arxiv-2610.19698 Sparse Blocked context only

Oct 14, 2026
Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
arxiv-2610.19628 Sparse Blocked context only

Oct 14, 2026
Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs
arxiv-2610.19613 Sparse Blocked context only

Oct 14, 2026
Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
arxiv-2610.19439 Sparse Blocked context only

Oct 14, 2026
Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach
arxiv-2610.19425 Sparse Blocked context only

Oct 14, 2026
AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety
arxiv-2610.19422 Sparse Blocked context only

Oct 14, 2026
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents
arxiv-2610.19376 Sparse Blocked context only

Oct 14, 2026
VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement
arxiv-2610.19361 Sparse Blocked context only

Oct 14, 2026
Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
arxiv-2610.19264 Sparse Blocked context only

Oct 13, 2026
CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline
arxiv-2610.19128 Sparse Blocked context only

Oct 13, 2026
Joint Subspace Sparse Attention for Efficient Long-Context Decoding
arxiv-2610.19026 Curated Related Blocked context only

Oct 13, 2026
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
arxiv-2610.18868 Sparse Blocked context only

Oct 13, 2026
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
arxiv-2610.18860 Direct Blocked context only

Oct 13, 2026
Beyond the Verdict: Agentic Code Judging with Verifiable Feedback
arxiv-2610.18760 Sparse Blocked context only

Oct 13, 2026
PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
arxiv-2610.18755 Sparse Blocked context only

Oct 13, 2026
VideoJev: System One Model for Video Understanding and Interaction
arxiv-2610.18615 Direct Blocked context only

Oct 13, 2026
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
arxiv-2610.18614 Sparse Blocked context only

Oct 13, 2026
LLM2R: From Large Language Models to 3D Reassemblers
arxiv-2610.18604 Sparse Blocked context only

Oct 13, 2026
Rethinking Projector Training in Multimodal LLMs
arxiv-2610.18598 Sparse Blocked context only

Oct 13, 2026
ReTerm: Recovery Training for Self-Improving Terminal Agents
arxiv-2610.18484 Sparse Blocked context only

Oct 13, 2026
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
arxiv-2610.18356 Curated Related Blocked context only

Oct 13, 2026
Choosing LLMs for Strategic Agent Interactions
arxiv-2610.18354 Sparse Blocked context only

Oct 13, 2026
Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation
arxiv-2610.18352 Sparse Blocked context only

Oct 13, 2026
Virtual Head Attention
arxiv-2610.17959 Sparse Blocked context only

Oct 13, 2026
Agent-Reflex: Teaching Language Agents to Act Reflectively
arxiv-2610.17953 Sparse Blocked context only

Oct 13, 2026
Learning How to Remember: Memory Modality Selection for GUI Agents
arxiv-2610.17928 Sparse Blocked context only

Oct 13, 2026
Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
arxiv-2610.17832 Sparse Blocked context only

Oct 13, 2026
Evidence-First Agentic Verification
arxiv-2610.17724 Sparse Blocked context only

Oct 13, 2026
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
arxiv-2610.17656 Sparse Blocked context only

Oct 13, 2026
FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
arxiv-2610.17552 Direct Blocked context only

Oct 13, 2026
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
arxiv-2610.17309 Direct Blocked context only

Oct 12, 2026
The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow
arxiv-2610.17301 Sparse Blocked context only

Oct 12, 2026
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
arxiv-2610.17246 Sparse Blocked context only

Oct 12, 2026
Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?
arxiv-2610.17079 Sparse Blocked context only

Oct 12, 2026
PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation
arxiv-2610.16355 Sparse Blocked context only

Oct 12, 2026
Self-Distillation with Verbal Regularization
arxiv-2610.16354 Sparse Blocked context only

Oct 12, 2026
EventLens: Event-Structure Reinforcement Learning for Video Understanding
arxiv-2610.16172 Sparse Blocked context only

Oct 12, 2026
Omni-Modal LLMs Know More Than They Say
arxiv-2610.16135 Sparse Blocked context only

Oct 12, 2026
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
arxiv-2610.16105 Sparse Blocked context only

Oct 12, 2026
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
arxiv-2610.15924 Sparse Blocked context only

Oct 11, 2026
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
arxiv-2610.15782 Sparse Blocked context only

Oct 11, 2026
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
arxiv-2610.15765 Sparse Blocked context only

Oct 11, 2026
SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
arxiv-2610.15725 Sparse Blocked context only

Oct 11, 2026
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
arxiv-2610.15715 Sparse Blocked context only

Oct 11, 2026
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
arxiv-2610.15542 Sparse Blocked context only

Oct 11, 2026
Words to World: Benchmarking LLMs in Interactive Physical Environments
arxiv-2610.15228 Sparse Blocked context only

Oct 10, 2026
PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
arxiv-2610.15208 Sparse Blocked context only

Oct 10, 2026
Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving
arxiv-2610.15112 Sparse Blocked context only

Oct 10, 2026
ProgAgent: Learning Tool Orchestration through Programmatic Training
arxiv-2610.14774 Sparse Blocked context only

Oct 10, 2026
LightVAE: Towards Compact and Efficient Video Autoencoders
arxiv-2610.14726 Sparse Blocked context only

Oct 10, 2026
EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment
arxiv-2610.14609 Direct Blocked context only

Oct 10, 2026
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
arxiv-2610.33024 Sparse Blocked context only

Oct 10, 2026
Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval
arxiv-2610.14465 Sparse Blocked context only

Oct 10, 2026
Learning Transferable World-Action Models from Task-Paired Human Videos
arxiv-2610.14351 Sparse Blocked context only

Oct 9, 2026
The Thinking Leakage in Reinforcement Learning for LLMs
arxiv-2610.14270 Sparse Blocked context only

Oct 9, 2026
SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing
arxiv-2610.14253 Sparse Blocked context only

Oct 9, 2026
Speech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription
arxiv-2610.14232 Sparse Blocked context only

Oct 9, 2026
Latent World Action Model for GUI Agents
arxiv-2610.14228 Sparse Blocked context only

Oct 9, 2026
InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
arxiv-2610.13944 Sparse Blocked context only

Oct 9, 2026
Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
arxiv-2610.14162 Direct Blocked context only

Oct 9, 2026
Multi-Stream Attention Residuals
arxiv-2610.13630 Sparse Blocked context only

Oct 9, 2026
ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning
arxiv-2610.13316 Sparse Blocked context only

Oct 9, 2026
Jag: Direct Box Prediction for Efficient Visual Grounding
arxiv-2610.13239 Sparse Blocked context only

Oct 9, 2026
PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
arxiv-2610.13171 Sparse Blocked context only

Oct 9, 2026
Continually Post-training Small Models via Synthetic Self-distillation
arxiv-2610.13113 Sparse Blocked context only

Oct 9, 2026
KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse
arxiv-2610.13060 Sparse Blocked context only

Oct 9, 2026
CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation
arxiv-2610.13059 Sparse Blocked context only

Oct 9, 2026
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
arxiv-2610.12939 Sparse Blocked context only

Oct 9, 2026
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
arxiv-2610.12933 Sparse Blocked context only

Oct 9, 2026
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
arxiv-2610.12611 Sparse Blocked context only

Oct 8, 2026
One Model to Loop Them All: Elastic Latent Recurrence for Language Models
arxiv-2610.12582 Sparse Blocked context only

Oct 8, 2026
Contextual Correction of Parallel Draftsfor Speculative Decoding
arxiv-2610.12570 Sparse Blocked context only

Oct 8, 2026
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
arxiv-2610.12468 Sparse Blocked context only

Oct 8, 2026
Pristine Models
arxiv-2610.14091 Sparse Blocked context only

Oct 8, 2026
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
arxiv-2610.12448 Sparse Blocked context only

Oct 8, 2026
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
arxiv-2610.12442 Sparse Blocked context only

Oct 8, 2026
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
arxiv-2610.12419 Sparse Blocked context only

Oct 8, 2026
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
arxiv-2610.12355 Sparse Blocked context only

Oct 8, 2026
Reasoning-Informed Visual Editing
arxiv-2610.12343 Sparse Blocked context only

Oct 8, 2026
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
arxiv-2610.12327 Sparse Blocked context only

Oct 8, 2026
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
arxiv-2610.12289 Sparse Blocked context only

Oct 8, 2026
TokenRouter: Efficient Serving System for Token-Level LLM Routing
arxiv-2610.12242 Sparse Blocked context only

Oct 8, 2026
From Prompting to Composing: A Spatial Canvas Interface for Poster Generation
arxiv-2610.12230 Sparse Blocked context only

Oct 8, 2026
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
arxiv-2610.12183 Sparse Blocked context only

Oct 8, 2026
SuperNav: An Agentic Navigation System for Any Task in Any Scene
arxiv-2610.12126 Sparse Blocked context only

Oct 8, 2026
Universal Textual Teaching for LLMs
arxiv-2610.12114 Sparse Blocked context only

Oct 8, 2026
Few-Step Generation via Data-Space Iteration
arxiv-2610.12102 Sparse Blocked context only

Oct 8, 2026
DataVista: Diagnosing Multimodal LLMs on Data Video Understanding
arxiv-2610.11993 Sparse Blocked context only

Oct 8, 2026
When History Helps and Hurts: Selective History Use across Multimodal Turns
arxiv-2610.11948 Sparse Blocked context only

Oct 8, 2026
Thinking Inertia: LLMs Keep Thinking When Told Not To
arxiv-2610.11765 Sparse Blocked context only

Oct 8, 2026
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
arxiv-2610.11570 Sparse Blocked context only

Oct 8, 2026
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
arxiv-2610.11366 Sparse Blocked context only

Oct 8, 2026
V-CoLA: Vision Token Compression with Linear Attention
arxiv-2610.11251 Sparse Blocked context only

Oct 8, 2026
The Lattice of Transition Laws
arxiv-2610.11216 Sparse Blocked context only

Oct 8, 2026
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
arxiv-2610.11169 Sparse Blocked context only

Oct 8, 2026
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
arxiv-2610.10787 Sparse Blocked context only

Oct 7, 2026
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
arxiv-2610.10533 Sparse Blocked context only

Oct 7, 2026
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
arxiv-2610.10455 Sparse Blocked context only

Oct 7, 2026
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets
arxiv-2610.09872 Sparse Blocked context only

Oct 7, 2026
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
arxiv-2610.09832 Sparse Blocked context only

Oct 7, 2026
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
arxiv-2610.09772 Sparse Blocked context only

Oct 7, 2026
Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving
arxiv-2610.09769 Sparse Blocked context only

Oct 7, 2026
From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
arxiv-2610.09684 Sparse Blocked context only

Oct 7, 2026
Coding-Agent Benchmarks Should Match Their Users' Task Flows
arxiv-2610.09633 Sparse Blocked context only

Oct 7, 2026
Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
arxiv-2610.09607 Sparse Blocked context only

Oct 7, 2026
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
arxiv-2610.09496 Sparse Blocked context only

Oct 7, 2026
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
arxiv-2610.23928 Sparse Blocked context only

Oct 7, 2026
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
arxiv-2610.09146 Sparse Blocked context only

Oct 6, 2026
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
arxiv-2610.09087 Sparse Blocked context only

Oct 6, 2026
PAIR: Bridging Perception and Action in Vision-Language-Action Models
arxiv-2610.09016 Sparse Blocked context only

Oct 6, 2026
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
arxiv-2610.08966 Sparse Blocked context only

Oct 6, 2026
IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
arxiv-2610.08781 Sparse Blocked context only

Oct 6, 2026
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
arxiv-2610.08773 Sparse Blocked context only

Oct 6, 2026
Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval
arxiv-2610.08716 Sparse Blocked context only

Oct 6, 2026
Agreement Is Not Validity: Cross-Model LLM Consensus in Diagnosing Student Failure Modes in K-12 Math Tutoring Dialogue
arxiv-2610.08703 Sparse Blocked context only

Oct 6, 2026
A Systematic Study of Small Language Models on Abstract Reasoning Tasks
arxiv-2610.08680 Sparse Blocked context only

Oct 6, 2026
Towards In-Parameter Memory Augmentation for Large Language Models
arxiv-2610.08630 Sparse Blocked context only

Oct 6, 2026
Incidental information contaminates patient notes and disrupts clinical reasoning in large language models
arxiv-2610.08585 Sparse Blocked context only

Oct 6, 2026
Latent space bias directions in LLMs capture confidence, not fairness
arxiv-2610.08559 Sparse Blocked context only

Oct 6, 2026
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
arxiv-2610.08452 Sparse Blocked context only

Oct 6, 2026
Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
arxiv-2610.08388 Sparse Blocked context only

Oct 6, 2026
Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation
arxiv-2610.08303 Sparse Blocked context only

Oct 6, 2026
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
arxiv-2610.08215 Sparse Blocked context only

Oct 6, 2026
Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation
arxiv-2610.08159 Sparse Blocked context only

Oct 6, 2026
Penalty-Framed No-Valid-Option MCQA: Analyzing LLM Abstention under Invalid Choices
arxiv-2610.08153 Sparse Blocked context only

Oct 6, 2026
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
arxiv-2610.08095 Sparse Blocked context only

Oct 6, 2026
DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs
arxiv-2610.08085 Sparse Blocked context only

Oct 6, 2026
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
arxiv-2610.07987 Sparse Blocked context only

Oct 6, 2026
Hybrid Latent Attention for Looped Language Models
arxiv-2610.07940 Sparse Blocked context only

Oct 6, 2026
Leveraging a four-quadrant approach for evaluating Redpine Science
arxiv-2610.07937 Sparse Blocked context only

Oct 6, 2026
Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing
arxiv-2610.07936 Sparse Blocked context only

Oct 6, 2026
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
arxiv-2610.07898 Sparse Blocked context only

Oct 6, 2026
Visual Abstention in Unified Multimodal Models
arxiv-2610.07887 Sparse Blocked context only

Oct 6, 2026
Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes
arxiv-2610.07853 Sparse Blocked context only

Oct 6, 2026
Dynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models
arxiv-2610.07848 Sparse Blocked context only

Oct 6, 2026
OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement
arxiv-2610.07847 Sparse Blocked context only

Oct 6, 2026
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
arxiv-2610.07832 Sparse Blocked context only

Oct 6, 2026
Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell
arxiv-2610.07782 Sparse Blocked context only

Oct 6, 2026
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
arxiv-2610.07767 Sparse Blocked context only

Oct 6, 2026
Learning to Retrieve via Reinforcement Learning in Embedding Space
arxiv-2610.07731 Sparse Blocked context only

Oct 6, 2026
SanSi: A Looped Typed Decision Model for System 1.5 Thinking
arxiv-2610.07730 Sparse Blocked context only

Oct 6, 2026
DLoop: Looped Speculative Decoding
arxiv-2610.07659 Sparse Blocked context only

Oct 6, 2026
Monte Carlo Estimation for KV Cache Eviction
arxiv-2610.07643 Sparse Blocked context only

Oct 6, 2026
Personal-Agent Mediated Recommendation with Cross-Platform User History
arxiv-2610.07588 Sparse Blocked context only

Oct 6, 2026
Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference
arxiv-2610.07587 Sparse Blocked context only

Oct 6, 2026
LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems
arxiv-2610.07580 Sparse Blocked context only

Oct 6, 2026
Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings
arxiv-2610.07572 Sparse Blocked context only

Oct 6, 2026
Quality-Aware Self-Correcting Speech Translation on an Edge Device
arxiv-2610.07545 Sparse Blocked context only

Oct 6, 2026
Disentangling Models from Personas in Heterogeneous LLM Simulations
arxiv-2610.07535 Sparse Blocked context only

Oct 6, 2026
On Open-Ended Information Seeking for Information Elicitation Agents
arxiv-2610.07509 Sparse Blocked context only

Oct 5, 2026
In With the Old: Enhancing 'Classical' Document Automation with Generative AI
arxiv-2610.07480 Sparse Blocked context only

Oct 5, 2026
Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
arxiv-2610.07348 Sparse Blocked context only

Oct 5, 2026
A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care
arxiv-2610.07339 Sparse Blocked context only

Oct 5, 2026
Structuring MoE Expert Selection for Agentic Reinforcement Learning
arxiv-2610.07332 Sparse Blocked context only

Oct 5, 2026
A theory of platonic representations in language models
arxiv-2610.07168 Sparse Blocked context only

Oct 5, 2026
Base Models Can Reason By Taking a Cue From Training Data
arxiv-2610.06851 Sparse Blocked context only

Oct 5, 2026
CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
arxiv-2610.07132 Sparse Blocked context only

Oct 5, 2026
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
arxiv-2610.06830 Sparse Blocked context only

Oct 5, 2026
Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
arxiv-2610.06804 Sparse Blocked context only

Oct 5, 2026
T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search
arxiv-2610.06782 Sparse Blocked context only

Oct 5, 2026
Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
arxiv-2610.06750 Sparse Blocked context only

Oct 5, 2026
SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection
arxiv-2610.06708 Sparse Blocked context only

Oct 5, 2026
MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks
arxiv-2610.06695 Sparse Blocked context only

Oct 5, 2026
Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation
arxiv-2610.06689 Sparse Blocked context only

Oct 5, 2026
Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs
arxiv-2610.06685 Sparse Blocked context only

Oct 5, 2026
The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
arxiv-2610.06673 Sparse Blocked context only

Oct 5, 2026
Reward Stealing Attack on Large Language Models
arxiv-2610.06670 Sparse Blocked context only

Oct 5, 2026
What Matters for Latent Reasoning with Flow Matching
arxiv-2610.06666 Sparse Blocked context only

Oct 5, 2026
Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents
arxiv-2610.06650 Curated Related Blocked context only

Oct 5, 2026
Representation-Space MMD for Diffusion Language Models
arxiv-2610.06648 Sparse Blocked context only

Oct 5, 2026
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
arxiv-2610.06647 Sparse Blocked context only

Oct 5, 2026
Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
arxiv-2610.06603 Sparse Blocked context only

Oct 5, 2026
Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants
arxiv-2610.06587 Sparse Blocked context only

Oct 5, 2026
Before Agent Tells The Lie: Has Deception Already Been Represented?
arxiv-2610.06576 Sparse Blocked context only

Oct 5, 2026
HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
arxiv-2610.06563 Sparse Blocked context only

Oct 5, 2026
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
arxiv-2610.06516 Sparse Blocked context only

Oct 5, 2026
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
arxiv-2610.06481 Sparse Blocked context only

Oct 5, 2026
Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation
arxiv-2610.05823 Sparse Blocked context only

Oct 5, 2026
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
arxiv-2610.07018 Sparse Blocked context only

Oct 4, 2026
Belief-Trajectory Energy: Measuring the Path to a Prediction
arxiv-2610.05114 Sparse Blocked context only

Oct 4, 2026
SearchJev: A Fast and Calibrated System-1 Model for Search Agents
arxiv-2610.05107 Sparse Blocked context only

Oct 4, 2026
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation
arxiv-2610.04977 Sparse Blocked context only

Oct 4, 2026
RobotUse: Allocating Computation, Context, and Decisions
arxiv-2610.04929 Sparse Blocked context only

Oct 4, 2026
Scaling Verifiable Environments for Long-horizon Work Agents
arxiv-2610.04906 Sparse Blocked context only

Oct 4, 2026
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
arxiv-2610.04875 Sparse Blocked context only

Oct 4, 2026
More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding
arxiv-2610.04753 Sparse Blocked context only

Oct 3, 2026
Agentic discovery of blood biomarker from distilled private health records
arxiv-2610.04749 Sparse Blocked context only

Oct 3, 2026
Understanding Errors in LLM-Based Question Answering over Imperfect Tables
arxiv-2610.04687 Sparse Blocked context only

Oct 3, 2026
DistScene: Object-to-Scene Distillation for 3D Scene Generation
arxiv-2610.06960 Sparse Blocked context only

Oct 3, 2026
PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training
arxiv-2610.04616 Sparse Blocked context only

Oct 3, 2026
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
arxiv-2610.03715 Sparse Blocked context only

Oct 2, 2026
Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models
arxiv-2610.03665 Sparse Blocked context only

Oct 2, 2026
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
arxiv-2610.03509 Sparse Blocked context only

Oct 2, 2026
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
arxiv-2610.03185 Sparse Blocked context only

Oct 2, 2026
Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
arxiv-2610.03136 Sparse Blocked context only

Oct 2, 2026
Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning
arxiv-2610.03102 Sparse Blocked context only

Oct 2, 2026
The Geometry of Knowledge Accessibility in Large Language Models
arxiv-2610.03052 Sparse Blocked context only

Oct 2, 2026
HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning
arxiv-2610.03039 Sparse Blocked context only

Oct 2, 2026
Tailoring the Quantization Space for 1-Bit KV Cache Compression
arxiv-2610.03027 Sparse Blocked context only

Oct 2, 2026
OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination
arxiv-2610.02999 Sparse Blocked context only

Oct 2, 2026
OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models
arxiv-2610.02986 Sparse Blocked context only

Oct 2, 2026
A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition
arxiv-2610.02970 Sparse Blocked context only

Oct 2, 2026
Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
arxiv-2610.02772 Sparse Blocked context only

Oct 2, 2026
Self-Supervised Scaling of Terminal Environments for Scientific Domains
arxiv-2610.02710 Sparse Blocked context only

Oct 2, 2026
OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies
arxiv-2610.02459 Sparse Blocked context only

Oct 1, 2026
Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance
arxiv-2610.02396 Sparse Blocked context only

Oct 1, 2026
Octrees as an Explicit 3D Language
arxiv-2610.02388 Sparse Blocked context only

Oct 1, 2026
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
arxiv-2610.02368 Sparse Blocked context only

Oct 1, 2026
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
arxiv-2610.02206 Sparse Blocked context only

Oct 1, 2026
ROWBench: Do Video Models Render What the Program Specifies?
arxiv-2610.02205 Sparse Blocked context only

Oct 1, 2026
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
arxiv-2610.02202 Sparse Blocked context only

Oct 1, 2026
Hierarchical Continuous Diffusion Language Models
arxiv-2610.02193 Sparse Blocked context only

Oct 1, 2026
The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models
arxiv-2610.02191 Sparse Blocked context only

Oct 1, 2026
Decoding Looped Transformers Better for (Almost) Free
arxiv-2610.02185 Sparse Blocked context only

Oct 1, 2026
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning
arxiv-2610.02181 Sparse Blocked context only

Oct 1, 2026
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
arxiv-2610.02148 Sparse Blocked context only

Oct 1, 2026
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
arxiv-2610.02142 Sparse Blocked context only

Oct 1, 2026
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
arxiv-2610.02117 Sparse Blocked context only

Oct 1, 2026
LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
arxiv-2610.02076 Sparse Blocked context only

Oct 1, 2026
Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities
arxiv-2610.01984 Sparse Blocked context only

Oct 1, 2026
Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models
arxiv-2610.01942 Sparse Blocked context only

Oct 1, 2026
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
arxiv-2610.01939 Direct Blocked context only

Oct 1, 2026
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
arxiv-2610.01595 Sparse Blocked context only

Oct 1, 2026
Sharpening Tax in Post-Training
arxiv-2610.01509 Sparse Blocked context only

Oct 1, 2026
VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
arxiv-2610.01499 Sparse Blocked context only

Oct 1, 2026
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
arxiv-2610.01415 Sparse Blocked context only

Oct 1, 2026
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
arxiv-2610.01092 Sparse Blocked context only

Oct 1, 2026
It Takes Workflows to Evolve Better Workflows
arxiv-2610.01026 Sparse Blocked context only

Oct 1, 2026
Scaling and Distilling Text Embeddings for Better Diffusibility
arxiv-2610.01016 Sparse Blocked context only

Oct 1, 2026
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
arxiv-2610.00972 Sparse Blocked context only

Oct 1, 2026
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
arxiv-2610.00906 Sparse Blocked context only

Oct 1, 2026
Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing
arxiv-2610.00825 Sparse Blocked context only

Sep 30, 2026
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
arxiv-2610.00686 Sparse Blocked context only

Sep 30, 2026
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
arxiv-2610.00559 Sparse Blocked context only

Sep 30, 2026
Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
arxiv-2610.00531 Sparse Blocked context only

Sep 30, 2026
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
arxiv-2610.00483 Sparse Blocked context only

Sep 30, 2026
Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text
arxiv-2609.40359 Sparse Blocked context only

Sep 30, 2026
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
arxiv-2609.40358 Sparse Blocked context only

Sep 30, 2026
I Have a Stream: Making Self-Supervised Learning Work on Continuous Video
arxiv-2609.40333 Sparse Blocked context only

Sep 30, 2026
EviRover: Reinforcing Agentic Perception Beyond a Glance
arxiv-2609.40230 Sparse Blocked context only

Sep 30, 2026
JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces
arxiv-2610.00437 Sparse Blocked context only

Sep 30, 2026
Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions
arxiv-2609.40124 Sparse Blocked context only

Sep 30, 2026
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
arxiv-2609.39982 Sparse Blocked context only

Sep 30, 2026
TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents
arxiv-2610.30161 Sparse Blocked context only

Sep 30, 2026
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
arxiv-2609.39661 Sparse Blocked context only

Sep 30, 2026
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
arxiv-2609.39601 Sparse Blocked context only

Sep 30, 2026
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
arxiv-2609.39578 Sparse Blocked context only

Sep 30, 2026
From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning
arxiv-2609.39566 Sparse Blocked context only

Sep 30, 2026
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
arxiv-2609.39533 Sparse Blocked context only

Sep 30, 2026
QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
arxiv-2609.39420 Sparse Blocked context only

Sep 30, 2026
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
arxiv-2609.39071 Sparse Blocked context only

Sep 30, 2026
SparseEngine: Sparse-First Inference Engine
arxiv-2609.39068 Direct Blocked context only

Sep 30, 2026
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
arxiv-2609.39045 Sparse Blocked context only

Sep 30, 2026
Does Learning Protein Folding Generalize to Broader Reasoning?
arxiv-2609.38879 Sparse Blocked context only

Sep 30, 2026
SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale
arxiv-2609.38822 Sparse Blocked context only

Sep 30, 2026
PatchHolmes: Agentic Patch Retrieval via Listwise Selection
arxiv-2609.38807 Sparse Blocked context only

Sep 30, 2026
Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation
arxiv-2609.38660 Sparse Blocked context only

Sep 29, 2026
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
arxiv-2609.38597 Direct Blocked context only

Sep 29, 2026

All archive pages