{"total":130,"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":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"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":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"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":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23,"area":"agents"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"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":"2607.14159","title":"MemoHarness: Agent Harnesses That Learn from Experience","created":"2026-07-14","cited_by_count":16,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"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":"2607.10891","title":"SETA: Scaling Environments for Terminal Agents","created":"2026-07-12","cited_by_count":12,"area":"agents"},{"id":"2601.16973","title":"VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents","created":"2026-01-23","cited_by_count":11,"area":"mllm"},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"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":"2508.02900","title":"Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game","created":"2025-08-04","cited_by_count":9,"area":null},{"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":"2602.20532","title":"Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training","created":"2026-02-24","cited_by_count":8,"area":null},{"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":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"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":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"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":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"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":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"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":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2602.20117","title":"ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models","created":"2026-02-23","cited_by_count":5,"area":"lr"},{"id":"2603.10793","title":"Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments","created":"2026-03-11","cited_by_count":5,"area":null},{"id":"2508.04280","title":"Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success","created":"2025-08-06","cited_by_count":4,"area":"mllm"},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"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":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2602.11424","title":"Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.15432","title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","created":"2026-03-16","cited_by_count":3,"area":"agents"},{"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":"2606.26122","title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2608.13567","title":"Modular Cognitive Architecture Emerges in Large Language Models","created":"2026-06-27","cited_by_count":3,"area":null},{"id":"2608.25518","title":"Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models","created":"2026-08-26","cited_by_count":3,"area":"wm"},{"id":"2506.06832","title":"Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures","created":"2025-06-07","cited_by_count":2,"area":null},{"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":"2609.08798","title":"Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation","created":"2026-09-08","cited_by_count":2,"area":"distill"},{"id":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2603.20219","title":"Thinking into the Future: Latent Lookahead Training for Transformers","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"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":"2604.17842","title":"QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks","created":"2026-04-20","cited_by_count":1,"area":null},{"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":"2605.06869","title":"Agentick: A Unified Benchmark for General Sequential Decision-Making Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.31509","title":"Skill Reuse as Compression in Agentic RL","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"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":"2608.16739","title":"Le Critique: Privileged Value Functions for LLM Reinforcement Learning","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2609.07183","title":"CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.21561","title":"On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation","created":"2026-09-18","cited_by_count":1,"area":"distill"},{"id":"2609.35641","title":"Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts","created":"2026-09-28","cited_by_count":1,"area":"mllm"},{"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":"2605.30788","title":"XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.31268","title":"Mellum2 Technical Report","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"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":"2606.22188","title":"Bayesian Adaptation Gym: A Benchmark for the Bayesian Low-Rank Adaptation of Multi-Modal Language Models","created":"2026-06-20","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}