{"total":68,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2511.19773","title":"Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs","created":"2025-11-24","cited_by_count":17,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2511.11584","title":"Output Supervision Can Obfuscate the Chain of Thought","created":"2025-10-11","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":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"area":"lr"},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2510.03971","title":"What Can You Do When You Have Zero Rewards During RL?","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2511.10621","title":"SSR: Socratic Self-Refine for Large Language Model Reasoning","created":"2025-11-13","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2605.02909","title":"Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2512.01775","title":"How Does RL Post-training Induce Skill Composition? A Case Study on Countdown","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2509.18083","title":"Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning","created":"2025-09-22","cited_by_count":5,"area":"lr"},{"id":"2602.20117","title":"ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models","created":"2026-02-23","cited_by_count":5,"area":"lr"},{"id":"2509.08721","title":"Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2509.21482","title":"Learning to Reason with Mixture of Tokens","created":"2025-09-25","cited_by_count":3,"area":"lr"},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2606.01599","title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2509.20866","title":"On the Robustness of Answer Formats in Medical Reasoning Models","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.01581","title":"Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression","created":"2025-10-02","cited_by_count":2,"area":"lr"},{"id":"2511.20814","title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2603.02208","title":"Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2603.20219","title":"Thinking into the Future: Latent Lookahead Training for Transformers","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2605.06638","title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2606.06475","title":"RREDCoT: Segment-Level Reward Redistribution for Reasoning Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.20740","title":"VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2607.19790","title":"Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2510.03394","title":"Studying the Korean Word-Chain Game with RLVR: Mitigating Reward Conflicts via Curriculum Learning","created":"2025-10-03","cited_by_count":0,"area":"lr"},{"id":"2601.14695","title":"CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2602.00770","title":"Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2603.18953","title":"Context Bootstrapped Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.08401","title":"AIPO: Learning to Reason from Active Interaction","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.11666","title":"Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.18261","title":"Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2606.05464","title":"Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.18910","title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.14895","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2608.18574","title":"Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.30936","title":"Self-Play Search Distillation for Large Language Model Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33781","title":"Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35426","title":"Frontier Learning: Training LLM Reasoners at the Edge of Capability","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38409","title":"ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.39632","title":"Towards Better Exploration in Sequential Test-Time Scaling","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.09587","title":"Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.17824","title":"Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}