{"total":223,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379,"area":"lr"},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810,"area":"lr"},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444,"area":"lr"},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"area":"lr"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2501.03262","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","created":"2025-01-04","cited_by_count":241,"area":"lr"},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165,"area":"lr"},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2503.01491","title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret","created":"2025-03-03","cited_by_count":98,"area":"lr"},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2412.15287","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","created":"2024-12-18","cited_by_count":89,"area":"lr"},{"id":"2505.15107","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","created":"2025-05-21","cited_by_count":88,"area":"lr"},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79,"area":"lr"},{"id":"2505.11821","title":"Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment","created":"2025-05-17","cited_by_count":79,"area":"lr"},{"id":"2402.01391","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","created":"2024-02-02","cited_by_count":77,"area":"lr"},{"id":"2511.08325","title":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","created":"2025-11-11","cited_by_count":77,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2501.12368","title":"InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model","created":"2025-01-21","cited_by_count":74,"area":"lr"},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"area":"lr"},{"id":"2504.21233","title":"Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2502.19655","title":"Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning","created":"2025-02-27","cited_by_count":40,"area":"lr"},{"id":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2505.17621","title":"Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2505.17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","created":"2025-05-22","cited_by_count":31,"area":"lr"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2505.13438","title":"Optimizing Anytime Reasoning via Budget Relative Policy Optimization","created":"2025-05-19","cited_by_count":27,"area":"lr"},{"id":"2509.18314","title":"Exploiting Tree Structure for Credit Assignment in RL Training of LLMs","created":"2025-09-22","cited_by_count":27,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"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":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2509.20712","title":"CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning","created":"2025-09-25","cited_by_count":23,"area":"lr"},{"id":"2410.09302","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","created":"2024-10-11","cited_by_count":22,"area":"lr"},{"id":"2503.15952","title":"Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning","created":"2025-03-20","cited_by_count":21,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2505.09316","title":"Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging","created":"2025-05-14","cited_by_count":20,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2506.11442","title":"ReVeal: Self-Evolving Code Agents via Reliable Self-Verification","created":"2025-06-13","cited_by_count":18,"area":"lr"},{"id":"2412.18279","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization","created":"2024-12-24","cited_by_count":17,"area":"lr"},{"id":"2506.01369","title":"Incentivizing LLMs to Self-Verify Their Answers","created":"2025-06-02","cited_by_count":17,"area":"lr"},{"id":"2506.01413","title":"Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models","created":"2025-06-02","cited_by_count":17,"area":"lr"},{"id":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2505.16265","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models","created":"2025-05-22","cited_by_count":16,"area":"lr"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"id":"2507.02962","title":"RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism","created":"2025-06-30","cited_by_count":16,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2509.25026","title":"GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2505.04842","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers","created":"2025-05-07","cited_by_count":14,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2604.11037","title":"RTMC: Step-Level Credit Assignment via Rollout Trees","created":"2026-04-13","cited_by_count":12,"area":"lr"},{"id":"2607.14171","title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning","created":"2026-07-15","cited_by_count":12,"area":"lr"},{"id":"2505.15311","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2505.23224","title":"MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration","created":"2025-05-29","cited_by_count":11,"area":"lr"},{"id":"2507.14295","title":"A Simple \"Try Again\" Can Elicit Multi-Turn LLM Reasoning","created":"2025-07-18","cited_by_count":11,"area":"lr"},{"id":"2507.19766","title":"UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities","created":"2025-07-26","cited_by_count":11,"area":"lr"},{"id":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.01656","title":"Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","cited_by_count":10,"area":"lr"},{"id":"2605.22263","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2504.12749","title":"LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection","created":"2025-04-17","cited_by_count":9,"area":"lr"},{"id":"2504.19524","title":"LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoning","created":"2025-04-28","cited_by_count":9,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2508.03058","title":"VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training","created":"2025-08-05","cited_by_count":9,"area":"lr"},{"id":"2508.07616","title":"ThinkTuning: Instilling Cognitive Reflections without Distillation","created":"2025-08-11","cited_by_count":9,"area":"lr"}],"next_cursor":"100"}