{"total":106,"rows":[{"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":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2606.07082","title":"On the Geometry of On-Policy Distillation","created":"2026-06-05","cited_by_count":19,"area":"lr"},{"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":"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":"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":"2606.05241","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":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"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":"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":"2605.30002","title":"KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2607.05943","title":"SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation","created":"2026-07-07","cited_by_count":5,"area":"lr"},{"id":"2608.11829","title":"Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling","created":"2026-08-12","cited_by_count":5,"area":"lr"},{"id":"2605.15777","title":"SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2606.18810","title":"Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2608.19408","title":"Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress","created":"2026-08-19","cited_by_count":3,"area":"lr"},{"id":"2608.25920","title":"Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems","created":"2026-08-26","cited_by_count":3,"area":"lr"},{"id":"2605.28184","title":"Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.22694","title":"SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding","created":"2026-06-21","cited_by_count":2,"area":"lr"},{"id":"2607.01237","title":"KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2608.01358","title":"HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning","created":"2026-08-02","cited_by_count":2,"area":"lr"},{"id":"2608.02867","title":"BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2608.12764","title":"Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents","created":"2026-08-13","cited_by_count":2,"area":"lr"},{"id":"2608.27420","title":"Boosting LLM Exploration via Weak-Model Guidance in RLVR","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2608.27448","title":"TTPO: Test-Time Policy Optimization","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2605.27901","title":"The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.16149","title":"Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.03031","title":"CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2608.07968","title":"Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"id":"2608.09435","title":"Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models","created":"2026-08-10","cited_by_count":1,"area":"lr"},{"id":"2608.26550","title":"SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning","created":"2026-08-27","cited_by_count":1,"area":"lr"},{"id":"2609.02702","title":"Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers","created":"2026-09-02","cited_by_count":1,"area":"lr"},{"id":"2605.06219","title":"Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.19597","title":"LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2605.21654","title":"Value-Gradient Hypothesis of RL for LLMs","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2606.11675","title":"Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.20624","title":"In LLM Reasoning, there is Irrationality on top of Value Misalignment","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.21704","title":"When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation","created":"2026-06-19","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.19088","title":"DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2607.28478","title":"Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2607.28680","title":"TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.02101","title":"Cross-Domain Hybrid OPD for Generalizable Search Agents","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2608.03028","title":"Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.06347","title":"RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.08146","title":"Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.13667","title":"Second Thought: Reasoning in Parallel as LLM Agents Act and Observe","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.16033","title":"$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2608.18581","title":"From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.20564","title":"Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning","created":"2026-08-20","cited_by_count":0,"area":"lr"},{"id":"2608.24086","title":"EMRB: A Multi-Level Benchmark for Evaluating LLM Reasoning over Raw Electromagnetic Signals","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2608.29662","title":"ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.02849","title":"Post-Training Language Models for Gold-Medal Performance in Coding Competitions","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.07036","title":"Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.08156","title":"When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.10445","title":"Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.11709","title":"When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.22746","title":"ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.29518","title":"CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2609.32351","title":"From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32913","title":"Allspark: Weak to Strong Transfer via Alternating Chain of Thought","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33181","title":"SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33463","title":"Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33585","title":"IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34327","title":"Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34344","title":"Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34492","title":"PowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power Systems","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35347","title":"Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37304","title":"MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.37773","title":"OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38798","title":"GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39566","title":"From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39578","title":"Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39801","title":"RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39838","title":"Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.40079","title":"LongEmo: Towards Emotion Understanding and Reasoning in Long Videos","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01184","title":"ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.01236","title":"Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02478","title":"Tropical Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02703","title":"Learning to Revise Reasoning with Segment-wise On-Policy Distillation","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.03509","title":"Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.04596","title":"DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04882","title":"ResOPD: Tail Residualization for Sparse On-Policy Distillation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.05119","title":"LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.07835","title":"DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.08561","title":"Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.09671","title":"InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.10641","title":"Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.12061","title":"When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.14570","title":"PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.16449","title":"CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17777","title":"Beyond Belief Nesting: Rethinking Higher-Order Theory of Mind in Large Language Models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}