{"total":1040,"rows":[{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142,"area":"agents"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2605.18740","title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","created":"2026-05-18","cited_by_count":77,"area":"mllm"},{"id":"2605.03677","title":"Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe","created":"2026-05-05","cited_by_count":49,"area":"distill"},{"id":"2606.14249","title":"HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry","created":"2026-06-12","cited_by_count":47,"area":null},{"id":"2606.11709","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation","created":"2026-06-10","cited_by_count":45,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2606.01139","title":"SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision","created":"2026-05-31","cited_by_count":30,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2606.24597","title":"Qwen-AgentWorld: Language World Models for General Agents","created":"2026-06-23","cited_by_count":28,"area":"wm"},{"id":"2605.22166","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","created":"2026-05-21","cited_by_count":27,"area":"agents"},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"area":"distill"},{"id":"2605.05204","title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","created":"2026-05-06","cited_by_count":22,"area":"diffusion"},{"id":"2606.17573","title":"Cordon: Semantic Transactions for Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2606.17861","title":"GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2606.30616","title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","created":"2026-06-29","cited_by_count":22,"area":"agents"},{"id":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21,"area":"agents"},{"id":"2606.07082","title":"On the Geometry of On-Policy Distillation","created":"2026-06-05","cited_by_count":19,"area":"lr"},{"id":"2607.13399","title":"Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations","created":"2026-07-15","cited_by_count":19,"area":"distill"},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2607.09996","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","created":"2026-07-10","cited_by_count":18,"area":"agents"},{"id":"2607.26057","title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation","created":"2026-07-28","cited_by_count":18,"area":"distill"},{"id":"2606.05806","title":"When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents","created":"2026-06-04","cited_by_count":17,"area":"lr"},{"id":"2606.08432","title":"Trajectory-Refined Distillation","created":"2026-06-07","cited_by_count":16,"area":"distill"},{"id":"2608.02276","title":"Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories","created":"2026-08-03","cited_by_count":16,"area":"agents"},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2606.02388","title":"Policy and World Modeling Co-Training for Language Agents","created":"2026-06-01","cited_by_count":15,"area":"wm"},{"id":"2606.18394","title":"JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting","created":"2026-06-16","cited_by_count":15,"area":"inference"},{"id":"2608.24696","title":"On-policy Distillation with Verifiable Reward","created":"2026-08-25","cited_by_count":15,"area":"distill"},{"id":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2608.25927","title":"Code World Model: Coding Agent as World Brain","created":"2026-08-26","cited_by_count":14,"area":"wm"},{"id":"2605.07396","title":"Rubric-based On-policy Distillation","created":"2026-05-08","cited_by_count":13,"area":"alignment"},{"id":"2605.30833","title":"Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation","created":"2026-05-29","cited_by_count":13,"area":"lr"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2607.01071","title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","created":"2026-07-01","cited_by_count":12,"area":"agents"},{"id":"2607.10891","title":"SETA: Scaling Environments for Terminal Agents","created":"2026-07-12","cited_by_count":12,"area":"agents"},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","cited_by_count":11,"area":"agents"},{"id":"2605.09253","title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","created":"2026-05-10","cited_by_count":11,"area":"distill"},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11,"area":"agents"},{"id":"2606.06021","title":"OPRD: On-Policy Representation Distillation","created":"2026-06-04","cited_by_count":11,"area":"distill"},{"id":"2606.09471","title":"Escaping the KL Agreement Trap in On-Policy Distillation","created":"2026-06-08","cited_by_count":11,"area":"distill"},{"id":"2606.11559","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","created":"2026-06-10","cited_by_count":11,"area":"agents"},{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2606.10662","title":"Decentralized Multi-Agent Systems with Shared Context","created":"2026-06-09","cited_by_count":10,"area":"lr"},{"id":"2606.13657","title":"Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation","created":"2026-06-11","cited_by_count":10,"area":"distill"},{"id":"2607.01233","title":"Measuring the Gap Between Human and LLM Research Ideas","created":"2026-07-01","cited_by_count":10,"area":null},{"id":"2607.20083","title":"Co-Evolving LLM Evaluators and Policies via DynamicRubric","created":"2026-07-22","cited_by_count":10,"area":null},{"id":"2606.05241","title":"Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation","created":"2026-06-03","cited_by_count":9,"area":"lr"},{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2607.02592","title":"H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation","created":"2026-07-01","cited_by_count":9,"area":"distill"},{"id":"2608.18271","title":"Rethinking Privileged Information in On-Policy Self-Distillation","created":"2026-08-18","cited_by_count":9,"area":"distill"},{"id":"2608.18580","title":"FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis","created":"2026-08-19","cited_by_count":9,"area":null},{"id":"2605.06884","title":"Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2605.12741","title":"Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation","created":"2026-05-12","cited_by_count":8,"area":"distill"},{"id":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2606.20659","title":"Skill Coverage: A Test Adequacy Metric for Agent Skills","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2606.23416","title":"Detecting Malicious Agent Skills in the Wild using Attention","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2607.04425","title":"UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents","created":"2026-07-05","cited_by_count":8,"area":"agents"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2607.22334","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","created":"2026-07-24","cited_by_count":8,"area":"distill"},{"id":"2607.26246","title":"Weak-to-Strong On-Policy Distillation","created":"2026-07-28","cited_by_count":8,"area":"distill"},{"id":"2608.01679","title":"When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary","created":"2026-08-03","cited_by_count":8,"area":"agents"},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2605.07363","title":"MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":7,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2605.13950","title":"Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2605.29341","title":"WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction","created":"2026-05-28","cited_by_count":7,"area":"mllm"},{"id":"2605.30883","title":"TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking","created":"2026-05-29","cited_by_count":7,"area":"agents"},{"id":"2606.03565","title":"Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2606.25819","title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2607.12893","title":"MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations","created":"2026-07-14","cited_by_count":7,"area":"agents"},{"id":"2607.14186","title":"NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2608.01837","title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning","created":"2026-08-03","cited_by_count":7,"area":"agents"},{"id":"2608.27311","title":"Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification","created":"2026-08-27","cited_by_count":7,"area":"agents"},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2606.14302","title":"Retrospective Progress-Aware Self-Refinement for LLM Agent Training","created":"2026-06-12","cited_by_count":6,"area":"agents"},{"id":"2606.22793","title":"A Formula-Driven Survey and Research Agenda for On-Policy Distillation","created":"2026-06-22","cited_by_count":6,"area":"distill"},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.02502","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","created":"2026-07-02","cited_by_count":6,"area":"distill"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2608.14277","title":"SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning","created":"2026-08-14","cited_by_count":6,"area":"lr"},{"id":"2608.16578","title":"Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents","created":"2026-08-17","cited_by_count":6,"area":null},{"id":"2609.05198","title":"What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection","created":"2026-09-04","cited_by_count":6,"area":"lr"},{"id":"2604.27083","title":"Co-Evolving Policy Distillation","created":"2026-04-29","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2605.08234","title":"When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression","created":"2026-05-07","cited_by_count":5,"area":"inference"},{"id":"2605.10779","title":"LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments","created":"2026-05-11","cited_by_count":5,"area":"agents"}],"next_cursor":"100"}