Paper2Code archive

Paper archive page 45

Page 45 of 123. Links match the indexable papers sitemap inventory.

300 canonical paper links on this archive page.

Code as Agent Harness
arxiv-2605.18747 Curated Related Blocked context only

May 18, 2026
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
arxiv-2605.18746 Sparse Blocked context only

May 18, 2026
Actionable World Representation
arxiv-2605.18743 Sparse Blocked context only

May 18, 2026
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
arxiv-2605.18739 Curated Related Blocked context only

May 18, 2026
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
arxiv-2605.18703 Sparse Blocked context only

May 18, 2026
Lance: Unified Multimodal Modeling by Multi-Task Synergy
arxiv-2605.18678 Direct Blocked context only

May 18, 2026
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
arxiv-2605.18652 Sparse Blocked context only

May 18, 2026
Language-Switching Triggers Take a Latent Detour Through Language Models
arxiv-2605.18646 Sparse Blocked context only

May 18, 2026
Post-Trained MoE Can Skip Half Experts via Self-Distillation
arxiv-2605.18643 Sparse Blocked context only

May 18, 2026
SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science
arxiv-2605.18630 Sparse Blocked context only

May 18, 2026
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
arxiv-2605.18601 Direct Blocked context only

May 18, 2026
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
arxiv-2605.18577 Sparse Blocked context only

May 18, 2026
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
arxiv-2605.20258 Sparse Blocked context only

May 18, 2026
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
arxiv-2605.18401 Sparse Blocked context only

May 18, 2026
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
arxiv-2605.18287 Sparse Blocked context only

May 18, 2026
Context Memorization for Efficient Long Context Generation
arxiv-2605.18226 Sparse Blocked context only

May 18, 2026
SIREM: Speech-Informed MRI Reconstruction with Learned Sampling
arxiv-2605.18221 Sparse Blocked context only

May 18, 2026
KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference
arxiv-2605.18071 Sparse Blocked context only

May 18, 2026
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
arxiv-2605.18018 Sparse Blocked context only

May 18, 2026
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
arxiv-2605.17933 Sparse Blocked context only

May 18, 2026
Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA
arxiv-2605.17932 Sparse Blocked context only

May 18, 2026
Evaluating Cognitive Age Alignment in Interactive AI Agents
arxiv-2605.17894 Sparse Blocked context only

May 18, 2026
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
arxiv-2605.17873 Sparse Blocked context only

May 18, 2026
SNLP: Layer-Parallel Inference via Structured Newton Corrections
arxiv-2605.17842 Sparse Blocked context only

May 18, 2026
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
arxiv-2605.20244 Sparse Blocked context only

May 18, 2026
Interactive Evaluation Requires a Design Science
arxiv-2605.17829 Sparse Blocked context only

May 18, 2026
Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning
arxiv-2605.17774 Sparse Blocked context only

May 18, 2026
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
arxiv-2605.17770 Sparse Blocked context only

May 18, 2026
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
arxiv-2605.17757 Curated Related Blocked context only

May 18, 2026
Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
arxiv-2605.17698 Sparse Blocked context only

May 17, 2026
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
arxiv-2605.17694 Sparse Blocked context only

May 17, 2026
Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification
arxiv-2605.17691 Sparse Blocked context only

May 17, 2026
AI Agents May Always Fall for Prompt Injections
arxiv-2605.17634 Sparse Blocked context only

May 17, 2026
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
arxiv-2605.17602 Sparse Blocked context only

May 17, 2026
How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
arxiv-2605.17570 Sparse Blocked context only

May 17, 2026
Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
arxiv-2605.17558 Sparse Blocked context only

May 17, 2026
RAG-based EEG-to-Text Translation Using Deep Learning and LLMs
arxiv-2605.17503 Sparse Blocked context only

May 17, 2026
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
arxiv-2605.17467 Sparse Blocked context only

May 17, 2026
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
arxiv-2605.17447 Sparse Blocked context only

May 17, 2026
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
arxiv-2605.17444 Sparse Blocked context only

May 17, 2026
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
arxiv-2605.17435 Sparse Blocked context only

May 17, 2026
QQJ: Quantifying Qualitative Judgment for Scalable and Human-Aligned Evaluation of Generative AI
arxiv-2605.17382 Sparse Blocked context only

May 17, 2026
Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
arxiv-2605.17360 Sparse Blocked context only

May 17, 2026
Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains
arxiv-2605.17359 Sparse Blocked context only

May 17, 2026
AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
arxiv-2605.17352 Sparse Blocked context only

May 17, 2026
Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution
arxiv-2605.17348 Sparse Blocked context only

May 17, 2026
Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
arxiv-2605.17342 Sparse Blocked context only

May 17, 2026
CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models
arxiv-2605.17305 Sparse Blocked context only

May 17, 2026
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
arxiv-2605.17295 Sparse Blocked context only

May 17, 2026
OProver: A Unified Framework for Agentic Formal Theorem Proving
arxiv-2605.17283 Curated Related Blocked context only

May 17, 2026
LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
arxiv-2605.17260 Sparse Blocked context only

May 17, 2026
From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements
arxiv-2605.17242 Sparse Blocked context only

May 17, 2026
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
arxiv-2605.17228 Sparse Blocked context only

May 17, 2026
OpenJarvis: Personal AI, On Personal Devices
arxiv-2605.17172 Direct Blocked context only

May 16, 2026
The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning
arxiv-2605.17113 Sparse Blocked context only

May 16, 2026
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
arxiv-2605.17110 Sparse Blocked context only

May 16, 2026
HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
arxiv-2605.17093 Sparse Blocked context only

May 16, 2026
RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation
arxiv-2605.17072 Sparse Blocked context only

May 16, 2026
D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
arxiv-2605.17037 Sparse Blocked context only

May 16, 2026
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road
arxiv-2605.17026 Sparse Blocked context only

May 16, 2026
HalluScore: Large Language Model Hallucination Question Answering Benchmark
arxiv-2605.17007 Sparse Blocked context only

May 16, 2026
Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?
arxiv-2605.16996 Sparse Blocked context only

May 16, 2026
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
arxiv-2605.23986 Sparse Blocked context only

May 16, 2026
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
arxiv-2605.16941 Sparse Blocked context only

May 16, 2026
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
arxiv-2605.16928 Sparse Blocked context only

May 16, 2026
DriveSafe: A Framework for Risk Detection and Safety Suggestions in Driving Scenarios
arxiv-2605.16892 Sparse Blocked context only

May 16, 2026
PaliBench: A Multi-Reference Blueprint for Classical Language Translation Benchmarks
arxiv-2605.16881 Sparse Blocked context only

May 16, 2026
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
arxiv-2605.16865 Sparse Blocked context only

May 16, 2026
Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction
arxiv-2605.16848 Sparse Blocked context only

May 16, 2026
RTI-Bench: A Structured Dataset for Indian Right-to-Information Decision Analysis
arxiv-2605.16843 Direct Blocked context only

May 16, 2026
Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
arxiv-2605.16826 Sparse Blocked context only

May 16, 2026
Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
arxiv-2605.16824 Sparse Blocked context only

May 16, 2026
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
arxiv-2605.16819 Sparse Blocked context only

May 16, 2026
FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
arxiv-2605.16800 Sparse Blocked context only

May 16, 2026
TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition
arxiv-2605.16790 Sparse Blocked context only

May 16, 2026
The Unlearnability Phenomenon in RLVR for Language Models
arxiv-2605.16787 Sparse Blocked context only

May 16, 2026
Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free
arxiv-2605.16767 Sparse Blocked context only

May 16, 2026
EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers
arxiv-2605.16745 Sparse Blocked context only

May 16, 2026
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
arxiv-2605.16679 Direct Blocked context only

May 15, 2026
Look Before You Leap: Autonomous Exploration for LLM Agents
arxiv-2605.16143 Sparse Blocked context only

May 15, 2026
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
arxiv-2605.15963 Sparse Blocked context only

May 15, 2026
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
arxiv-2605.15961 Sparse Blocked context only

May 15, 2026
Unlocking Dense Metric Depth Estimation in VLMs
arxiv-2605.15876 Sparse Blocked context only

May 15, 2026
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
arxiv-2605.15871 Sparse Blocked context only

May 15, 2026
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
arxiv-2605.15764 Sparse Blocked context only

May 15, 2026
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
arxiv-2605.15759 Sparse Blocked context only

May 15, 2026
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
arxiv-2605.15726 Sparse Blocked context only

May 15, 2026
Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
arxiv-2605.15669 Sparse Blocked context only

May 15, 2026
Calibrating LLMs with Semantic-level Reward
arxiv-2605.15588 Sparse Blocked context only

May 15, 2026
Measuring Maximum Activations in Open Large Language Models
arxiv-2605.15572 Sparse Blocked context only

May 15, 2026
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
arxiv-2605.15565 Direct Blocked context only

May 15, 2026
RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
arxiv-2605.15514 Sparse Blocked context only

May 15, 2026
STS: Efficient Sparse Attention with Speculative Token Sparsity
arxiv-2605.15508 Sparse Blocked context only

May 15, 2026
FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models
arxiv-2605.15482 Sparse Blocked context only

May 14, 2026
Video Models Can Reason with Verifiable Rewards
arxiv-2605.15458 Sparse Blocked context only

May 14, 2026
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
arxiv-2605.15301 Sparse Blocked context only

May 14, 2026
PhysBrain 1.0 Technical Report
arxiv-2605.15298 Sparse Blocked context only

May 14, 2026
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
arxiv-2605.15193 Sparse Blocked context only

May 14, 2026
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
arxiv-2605.15190 Curated Related Blocked context only

May 14, 2026
From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
arxiv-2605.15181 Sparse Blocked context only

May 14, 2026
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
arxiv-2605.15178 Direct Blocked context only

May 14, 2026
ReactiveGWM: Steering NPC in Reactive Game World Models
arxiv-2605.15256 Sparse Blocked context only

May 14, 2026
Self-Distilled Agentic Reinforcement Learning
arxiv-2605.15155 Direct Blocked context only

May 14, 2026
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
arxiv-2605.15141 Direct Blocked context only

May 14, 2026
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
arxiv-2605.15055 Sparse Blocked context only

May 14, 2026
Orchard: An Open-Source Agentic Modeling Framework
arxiv-2605.15040 Direct Blocked context only

May 14, 2026
GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding
arxiv-2605.15250 Sparse Blocked context only

May 14, 2026
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
arxiv-2605.14978 Sparse Blocked context only

May 14, 2026
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
arxiv-2605.14928 Sparse Blocked context only

May 14, 2026
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
arxiv-2605.14906 Sparse Blocked context only

May 14, 2026
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
arxiv-2605.14876 Sparse Blocked context only

May 14, 2026
Holistic Evaluation and Failure Diagnosis of AI Agents
arxiv-2605.14865 Sparse Blocked context only

May 14, 2026
Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis
arxiv-2605.14842 Sparse Blocked context only

May 14, 2026
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
arxiv-2605.14747 Sparse Blocked context only

May 14, 2026
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
arxiv-2605.14712 Sparse Blocked context only

May 14, 2026
$π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
arxiv-2605.14678 Direct Blocked context only

May 14, 2026
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
arxiv-2605.14539 Sparse Blocked context only

May 14, 2026
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
arxiv-2605.14438 Sparse Blocked context only

May 14, 2026
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
arxiv-2605.14392 Sparse Blocked context only

May 14, 2026
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
arxiv-2605.14386 Sparse Blocked context only

May 14, 2026
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
arxiv-2605.14212 Curated Related Blocked context only

May 14, 2026
Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning
arxiv-2605.14040 Sparse Blocked context only

May 13, 2026
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
arxiv-2605.14038 Curated Related Blocked context only

May 13, 2026
Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
arxiv-2605.14005 Sparse Blocked context only

May 13, 2026
VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use
arxiv-2605.13989 Sparse Blocked context only

May 13, 2026
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
arxiv-2605.13831 Sparse Blocked context only

May 13, 2026
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
arxiv-2605.13941 Direct Blocked context only

May 13, 2026
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
arxiv-2605.13724 Direct Blocked context only

May 13, 2026
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
arxiv-2605.13647 Sparse Blocked context only

May 13, 2026
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
arxiv-2605.16409 Sparse Blocked context only

May 13, 2026
Qwen-Image-VAE-2.0 Technical Report
arxiv-2605.13565 Sparse Blocked context only

May 13, 2026
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
arxiv-2605.13542 Sparse Blocked context only

May 13, 2026
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
arxiv-2605.13511 Sparse Blocked context only

May 13, 2026
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
arxiv-2605.13481 Sparse Blocked context only

May 13, 2026
CogniFold: Always-On Proactive Memory via Cognitive Folding
arxiv-2605.13438 Direct Blocked context only

May 13, 2026
Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
arxiv-2605.18852 Sparse Blocked context only

May 13, 2026
Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
arxiv-2605.13360 Sparse Blocked context only

May 13, 2026
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
arxiv-2605.13169 Sparse Blocked context only

May 13, 2026
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
arxiv-2605.13062 Curated Related Blocked context only

May 13, 2026
Context Training with Active Information Seeking
arxiv-2605.13050 Sparse Blocked context only

May 13, 2026
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
arxiv-2605.13037 Sparse Blocked context only

May 13, 2026
When Vision Speaks for Sound
arxiv-2605.16403 Sparse Blocked context only

May 13, 2026
Useful Memories Become Faulty When Continuously Updated by LLMs
arxiv-2605.12978 Sparse Blocked context only

May 13, 2026
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
arxiv-2605.12925 Sparse Blocked context only

May 13, 2026
Revisiting DAgger in the Era of LLM-Agents
arxiv-2605.12913 Sparse Blocked context only

May 13, 2026
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
arxiv-2605.12882 Sparse Blocked context only

May 13, 2026
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
arxiv-2605.12825 Direct Blocked context only

May 12, 2026
Training Large Language Models to Predict Clinical Events
arxiv-2605.12817 Sparse Blocked context only

May 12, 2026
Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds
arxiv-2605.18827 Sparse Blocked context only

May 12, 2026
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
arxiv-2605.12684 Sparse Blocked context only

May 12, 2026
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
arxiv-2605.12501 Sparse Blocked context only

May 12, 2026
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
arxiv-2605.12500 Sparse Blocked context only

May 12, 2026
From Web to Pixels: Bringing Agentic Search into Visual Perception
arxiv-2605.12497 Sparse Blocked context only

May 12, 2026
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
arxiv-2605.12495 Sparse Blocked context only

May 12, 2026
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
arxiv-2605.12587 Sparse Blocked context only

May 12, 2026
Learning, Fast and Slow: Towards LLMs That Adapt Continually
arxiv-2605.12484 Sparse Blocked context only

May 12, 2026
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
arxiv-2605.12481 Sparse Blocked context only

May 12, 2026
Solve the Loop: Attractor Models for Language and Reasoning
arxiv-2605.12466 Sparse Blocked context only

May 12, 2026
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
arxiv-2605.12460 Sparse Blocked context only

May 12, 2026
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
arxiv-2605.12456 Sparse Blocked context only

May 12, 2026
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
arxiv-2605.12419 Sparse Blocked context only

May 12, 2026
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
arxiv-2605.12411 Sparse Blocked context only

May 12, 2026
$δ$-mem: Efficient Online Memory for Large Language Models
arxiv-2605.12357 Sparse Blocked context only

May 12, 2026
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
arxiv-2605.12305 Sparse Blocked context only

May 12, 2026
Targeted Neuron Modulation via Contrastive Pair Search
arxiv-2605.12290 Sparse Blocked context only

May 12, 2026
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
arxiv-2605.12288 Sparse Blocked context only

May 12, 2026
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
arxiv-2605.12070 Sparse Blocked context only

May 12, 2026
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
arxiv-2605.12034 Sparse Blocked context only

May 12, 2026
Learning Agentic Policy from Action Guidance
arxiv-2605.12004 Sparse Blocked context only

May 12, 2026
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
arxiv-2605.11882 Sparse Blocked context only

May 12, 2026
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
arxiv-2605.11854 Sparse Blocked context only

May 12, 2026
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
arxiv-2605.11739 Sparse Blocked context only

May 12, 2026
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
arxiv-2605.11733 Sparse Blocked context only

May 12, 2026
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration -- Learning from Cheap, Optimizing Expensive
arxiv-2605.11518 Sparse Blocked context only

May 12, 2026
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
arxiv-2605.11436 Sparse Blocked context only

May 12, 2026
UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
arxiv-2605.11400 Sparse Blocked context only

May 12, 2026
An Empirical Study of Automating Agent Evaluation
arxiv-2605.11378 Sparse Blocked context only

May 12, 2026
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
arxiv-2605.11182 Sparse Blocked context only

May 11, 2026
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
arxiv-2605.11136 Sparse Blocked context only

May 11, 2026
Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
arxiv-2605.10923 Sparse Blocked context only

May 11, 2026
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
arxiv-2605.10921 Sparse Blocked context only

May 11, 2026
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
arxiv-2605.10913 Direct Blocked context only

May 11, 2026
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
arxiv-2605.10912 Sparse Blocked context only

May 11, 2026
Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
arxiv-2605.10848 Sparse Blocked context only

May 11, 2026
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
arxiv-2605.10781 Sparse Blocked context only

May 11, 2026
Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring
arxiv-2605.16386 Sparse Blocked context only

May 11, 2026
Qwen-Image-2.0 Technical Report
arxiv-2605.10730 Sparse Blocked context only

May 11, 2026
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
arxiv-2605.16385 Sparse Blocked context only

May 11, 2026
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
arxiv-2605.10488 Sparse Blocked context only

May 11, 2026
SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
arxiv-2605.10453 Sparse Blocked context only

May 11, 2026
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
arxiv-2605.10434 Sparse Blocked context only

May 11, 2026
SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation
arxiv-2605.10376 Sparse Blocked context only

May 11, 2026
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
arxiv-2605.10365 Sparse Blocked context only

May 11, 2026
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
arxiv-2605.10344 Sparse Blocked context only

May 11, 2026
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
arxiv-2605.10341 Direct Blocked context only

May 11, 2026
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
arxiv-2605.10268 Sparse Blocked context only

May 11, 2026
IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs
arxiv-2605.10267 Sparse Blocked context only

May 11, 2026
Unsupervised Process Reward Models
arxiv-2605.10158 Sparse Blocked context only

May 11, 2026
Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework
arxiv-2605.10043 Sparse Blocked context only

May 11, 2026
PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning
arxiv-2605.10032 Sparse Blocked context only

May 11, 2026
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
arxiv-2605.09996 Sparse Blocked context only

May 11, 2026
Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference
arxiv-2605.09990 Sparse Blocked context only

May 11, 2026
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
arxiv-2605.09942 Sparse Blocked context only

May 11, 2026
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
arxiv-2605.09936 Direct Blocked context only

May 11, 2026
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
arxiv-2605.09932 Sparse Blocked context only

May 11, 2026
Key-Value Means
arxiv-2605.09877 Direct Blocked context only

May 11, 2026
The Metacognitive Probe: Five Behavioural Calibration Diagnostics for LLMs
arxiv-2605.09844 Sparse Blocked context only

May 11, 2026
Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
arxiv-2605.09820 Sparse Blocked context only

May 10, 2026
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
arxiv-2605.09806 Sparse Blocked context only

May 10, 2026
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
arxiv-2605.09777 Sparse Blocked context only

May 10, 2026
Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
arxiv-2605.09665 Sparse Blocked context only

May 10, 2026
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
arxiv-2605.09635 Sparse Blocked context only

May 10, 2026
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
arxiv-2605.09618 Sparse Blocked context only

May 10, 2026
Edit-Based Refinement for Parallel Masked Diffusion Language Models
arxiv-2605.09603 Sparse Blocked context only

May 10, 2026
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
arxiv-2605.09548 Sparse Blocked context only

May 10, 2026
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
arxiv-2605.09530 Curated Related Blocked context only

May 10, 2026
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning
arxiv-2605.09490 Sparse Blocked context only

May 10, 2026
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
arxiv-2605.09423 Sparse Blocked context only

May 10, 2026
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
arxiv-2605.09269 Sparse Blocked context only

May 10, 2026
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
arxiv-2605.09266 Sparse Blocked context only

May 10, 2026
Reinforcing Multimodal Reasoning Against Visual Degradation
arxiv-2605.09262 Sparse Blocked context only

May 10, 2026
LLM Agents Already Know When to Call Tools -- Even Without Reasoning
arxiv-2605.09252 Sparse Blocked context only

May 10, 2026
RigidFormer: Learning Rigid Dynamics using Transformers
arxiv-2605.09196 Sparse Blocked context only

May 9, 2026
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
arxiv-2605.09131 Sparse Blocked context only

May 9, 2026
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
arxiv-2605.08985 Sparse Blocked context only

May 9, 2026
Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
arxiv-2605.08978 Direct Blocked context only

May 9, 2026
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
arxiv-2605.08738 Sparse Blocked context only

May 9, 2026
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
arxiv-2605.08737 Sparse Blocked context only

May 9, 2026
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
arxiv-2605.08715 Sparse Blocked context only

May 9, 2026
RewardHarness: Self-Evolving Agentic Post-Training
arxiv-2605.08703 Sparse Blocked context only

May 9, 2026
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
arxiv-2605.08678 Sparse Blocked context only

May 9, 2026
PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
arxiv-2605.08646 Sparse Blocked context only

May 9, 2026
Large Language Models over Networks: Collaborative Intelligence under Resource Constraints
arxiv-2605.08626 Sparse Blocked context only

May 9, 2026
Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection
arxiv-2605.08583 Sparse Blocked context only

May 9, 2026
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
arxiv-2605.08513 Sparse Blocked context only

May 8, 2026
A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
arxiv-2605.08504 Sparse Blocked context only

May 8, 2026
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
arxiv-2605.08472 Sparse Blocked context only

May 8, 2026
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
arxiv-2605.08083 Sparse Blocked context only

May 8, 2026
Flow-OPD: On-Policy Distillation for Flow Matching Models
arxiv-2605.08063 Sparse Blocked context only

May 8, 2026
Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning
arxiv-2605.08061 Sparse Blocked context only

May 8, 2026
CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
arxiv-2605.08057 Sparse Blocked context only

May 8, 2026
Fast Byte Latent Transformer
arxiv-2605.08044 Sparse Blocked context only

May 8, 2026
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
arxiv-2605.08029 Sparse Blocked context only

May 8, 2026
Tool Calling is Linearly Readable and Steerable in Language Models
arxiv-2605.07990 Sparse Blocked context only

May 8, 2026
Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
arxiv-2605.07937 Sparse Blocked context only

May 8, 2026
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
arxiv-2605.07924 Sparse Blocked context only

May 8, 2026
Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
arxiv-2605.07883 Sparse Blocked context only

May 8, 2026
KL for a KL: On-Policy Distillation with Control Variate Baseline
arxiv-2605.07865 Sparse Blocked context only

May 8, 2026
Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
arxiv-2605.07847 Sparse Blocked context only

May 8, 2026
Anisotropic Modality Align
arxiv-2605.07825 Sparse Blocked context only

May 8, 2026
CktFormalizer: Autoformalization of Natural Language into Circuit Representations
arxiv-2605.07782 Sparse Blocked context only

May 8, 2026
Tracing Uncertainty in Language Model "Reasoning"
arxiv-2605.07776 Sparse Blocked context only

May 8, 2026
TextLDM: Language Modeling with Continuous Latent Diffusion
arxiv-2605.07748 Sparse Blocked context only

May 8, 2026
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
arxiv-2605.07731 Sparse Blocked context only

May 8, 2026
SOD: Step-wise On-policy Distillation for Small Language Model Agents
arxiv-2605.07725 Sparse Blocked context only

May 8, 2026
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
arxiv-2605.07721 Sparse Blocked context only

May 8, 2026
Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning
arxiv-2605.07660 Sparse Blocked context only

May 8, 2026
Reliable Chain-of-Thought via Prefix Consistency
arxiv-2605.07654 Sparse Blocked context only

May 8, 2026
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
arxiv-2605.07647 Sparse Blocked context only

May 8, 2026
Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation
arxiv-2605.07613 Sparse Blocked context only

May 8, 2026
Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators
arxiv-2605.07600 Sparse Blocked context only

May 8, 2026
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
arxiv-2605.07579 Sparse Blocked context only

May 8, 2026
Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
arxiv-2605.07568 Sparse Blocked context only

May 8, 2026
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
arxiv-2605.07501 Sparse Blocked context only

May 8, 2026
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
arxiv-2605.07461 Sparse Blocked context only

May 8, 2026
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
arxiv-2605.07447 Sparse Blocked context only

May 8, 2026
ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring
arxiv-2605.07415 Sparse Blocked context only

May 8, 2026
Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
arxiv-2605.07395 Sparse Blocked context only

May 8, 2026
BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
arxiv-2605.07394 Sparse Blocked context only

May 8, 2026
Gradient-Based LoRA Rank Allocation Under GRPO: An Empirical Study
arxiv-2605.07366 Sparse Blocked context only

May 8, 2026
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
arxiv-2605.07363 Sparse Blocked context only

May 8, 2026
LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification
arxiv-2605.07315 Sparse Blocked context only

May 8, 2026
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
arxiv-2605.07248 Sparse Blocked context only

May 8, 2026
Teaching Language Models to Think in Code
arxiv-2605.07237 Sparse Blocked context only

May 8, 2026
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
arxiv-2605.07210 Sparse Blocked context only

May 8, 2026
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
arxiv-2605.07153 Sparse Blocked context only

May 8, 2026
Structural Rationale Distillation via Reasoning Space Compression
arxiv-2605.07139 Sparse Blocked context only

May 8, 2026
Region4Web: Rethinking Observation Space Granularity for Web Agents
arxiv-2605.07134 Sparse Blocked context only

May 8, 2026
The Position Curse: LLMs Struggle to Locate the Last Few Items in a List
arxiv-2605.07127 Sparse Blocked context only

May 8, 2026
ModelLens: Finding the Best for Your Task from Myriads of Models
arxiv-2605.07075 Sparse Blocked context only

May 8, 2026
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
arxiv-2605.07039 Sparse Blocked context only

May 7, 2026
A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency
arxiv-2605.06924 Sparse Blocked context only

May 7, 2026
Conformal Agent Error Attribution
arxiv-2605.06788 Sparse Blocked context only

May 7, 2026
UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
arxiv-2605.06665 Sparse Blocked context only

May 7, 2026
EMO: Pretraining Mixture of Experts for Emergent Modularity
arxiv-2605.06663 Sparse Blocked context only

May 7, 2026
Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
arxiv-2605.06650 Sparse Blocked context only

May 7, 2026
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
arxiv-2605.06642 Sparse Blocked context only

May 7, 2026
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
arxiv-2605.06643 Sparse Blocked context only

May 7, 2026
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
arxiv-2605.06638 Sparse Blocked context only

May 7, 2026
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
arxiv-2605.06635 Sparse Blocked context only

May 7, 2026
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
arxiv-2605.06597 Direct Blocked context only

May 7, 2026
Long Context Pre-Training with Lighthouse Attention
arxiv-2605.06554 Sparse Blocked context only

May 7, 2026
Continuous Latent Diffusion Language Model
arxiv-2605.06548 Sparse Blocked context only

May 7, 2026
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
arxiv-2605.06527 Sparse Blocked context only

May 7, 2026
PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
arxiv-2605.06455 Sparse Blocked context only

May 7, 2026
HumanNet: Scaling Human-centric Video Learning to One Million Hours
arxiv-2605.06747 Direct Blocked context only

May 7, 2026
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
arxiv-2605.06342 Sparse Blocked context only

May 7, 2026
MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
arxiv-2605.06334 Sparse Blocked context only

May 7, 2026
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
arxiv-2605.06327 Sparse Blocked context only

May 7, 2026
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
arxiv-2605.06320 Sparse Blocked context only

May 7, 2026

All archive pages