{"total":241,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326,"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":"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":"2508.04324","title":"TempFlow-GRPO: When Timing Matters for GRPO in Flow Models","created":"2025-08-06","cited_by_count":97,"area":"lr"},{"id":"2505.16410","title":"Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning","created":"2025-05-22","cited_by_count":72,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2601.05808","title":"EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis","created":"2026-01-09","cited_by_count":63,"area":"agents"},{"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":"2507.21892","title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","created":"2025-07-29","cited_by_count":52,"area":"rag"},{"id":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"id":"2505.16192","title":"VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought","created":"2025-05-22","cited_by_count":49,"area":"lr"},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2503.16188","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","created":"2025-03-20","cited_by_count":44,"area":"lr"},{"id":"2505.15034","title":"RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning","created":"2025-05-21","cited_by_count":40,"area":"lr"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2509.21268","title":"MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources","created":"2025-09-25","cited_by_count":39,"area":"lr"},{"id":"2508.03440","title":"LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking","created":"2025-08-05","cited_by_count":38,"area":"lr"},{"id":"2509.23040","title":"Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents","created":"2025-09-27","cited_by_count":38,"area":"lr"},{"id":"2506.17219","title":"No Free Lunch: Rethinking Internal Feedback for LLM Reasoning","created":"2025-06-20","cited_by_count":37,"area":"lr"},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"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":"2505.17508","title":"On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning","created":"2025-05-23","cited_by_count":30,"area":"lr"},{"id":"2506.09016","title":"SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning","created":"2025-06-10","cited_by_count":29,"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":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27,"area":"lr"},{"id":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"id":"2505.02391","title":"Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL","created":"2025-05-05","cited_by_count":24,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2506.00070","title":"Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics","created":"2025-05-29","cited_by_count":21,"area":"lr"},{"id":"2510.02240","title":"RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2505.24630","title":"Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models","created":"2025-05-30","cited_by_count":19,"area":"lr"},{"id":"2510.01037","title":"CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs","created":"2025-10-01","cited_by_count":19,"area":"lr"},{"id":"2505.10554","title":"Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models","created":"2025-05-15","cited_by_count":18,"area":"lr"},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17,"area":"lr"},{"id":"2510.01132","title":"A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning","created":"2025-10-01","cited_by_count":17,"area":"agents"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","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":"2505.21668","title":"R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2506.12935","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","created":"2025-06-15","cited_by_count":15,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"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":"2502.13389","title":"Reasoning with Reinforced Functional Token Tuning","created":"2025-02-19","cited_by_count":14,"area":"lr"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2511.16665","title":"Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter","created":"2025-11-20","cited_by_count":14,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2604.11784","title":"ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents","created":"2026-04-13","cited_by_count":14,"area":"agents"},{"id":"2505.12432","title":"Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning","created":"2025-05-18","cited_by_count":13,"area":"lr"},{"id":"2505.15259","title":"ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search","created":"2025-05-21","cited_by_count":13,"area":"lr"},{"id":"2510.18924","title":"Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients","created":"2025-10-21","cited_by_count":13,"area":"lr"},{"id":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"area":"lr"},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","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":"2505.21765","title":"Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models","created":"2025-05-27","cited_by_count":11,"area":"lr"},{"id":"2510.11620","title":"Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","cited_by_count":10,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2509.23392","title":"Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking","created":"2025-09-27","cited_by_count":10,"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":"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":"2603.21563","title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration","created":"2026-03-23","cited_by_count":10,"area":"lr"},{"id":"2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","created":"2026-03-26","cited_by_count":10,"area":"lr"},{"id":"2505.17652","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2601.03823","title":"Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning","created":"2026-01-07","cited_by_count":9,"area":"lr"},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2606.01281","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","created":"2026-05-31","cited_by_count":9,"area":"lr"},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2504.10187","title":"DeepTrans: Deep Reasoning Translation via Reinforcement Learning","created":"2025-04-14","cited_by_count":8,"area":"lr"},{"id":"2505.12717","title":"ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving","created":"2025-05-19","cited_by_count":8,"area":"lr"},{"id":"2505.16176","title":"Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2510.25206","title":"RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models","created":"2025-10-29","cited_by_count":8,"area":"lr"},{"id":"2512.17306","title":"Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images","created":"2025-12-19","cited_by_count":8,"area":"lr"},{"id":"2512.18215","title":"Stable and Efficient Single-Rollout RL for Multimodal Reasoning","created":"2025-12-20","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":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2604.18401","title":"CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities","created":"2026-04-20","cited_by_count":8,"area":"agents"},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"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":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2606.26027","title":"Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2602.06554","title":"SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees","created":"2026-02-06","cited_by_count":6,"area":"agents"},{"id":"2602.09598","title":"Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning","created":"2026-02-10","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":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2604.19485","title":"EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training","created":"2026-04-21","cited_by_count":6,"area":"lr"},{"id":"2505.12744","title":"Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation","created":"2025-05-19","cited_by_count":5,"area":"lr"},{"id":"2506.20241","title":"Enhancing Large Language Models through Structured Reasoning","created":"2025-06-25","cited_by_count":5,"area":"lr"},{"id":"2507.22716","title":"From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs","created":"2025-07-30","cited_by_count":5,"area":"lr"}],"next_cursor":"100"}