{"total":289,"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":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"area":"lr"},{"id":"2510.04206","title":"AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework","created":"2025-10-05","cited_by_count":62,"area":"agents"},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62,"area":"lr"},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2511.16108","title":"SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent","created":"2025-11-20","cited_by_count":48,"area":"agents"},{"id":"2510.07284","title":"Online Rubrics Elicitation from Pairwise Comparisons","created":"2025-10-08","cited_by_count":46,"area":null},{"id":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"area":"lr"},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2510.15047","title":"Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective","created":"2025-10-16","cited_by_count":28,"area":"wm"},{"id":"2511.15605","title":"SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models","created":"2025-11-19","cited_by_count":27,"area":"vla"},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25,"area":"diffusion"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2509.25849","title":"Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"area":"lr"},{"id":"2603.09206","title":"MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data","created":"2026-03-10","cited_by_count":21,"area":"lr"},{"id":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","cited_by_count":19,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2603.02146","title":"LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards","created":"2026-03-02","cited_by_count":15,"area":"lr"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2509.23958","title":"Reinforcement Learning with Inverse Rewards for World Model Post-training","created":"2025-09-28","cited_by_count":13,"area":"wm"},{"id":"2509.25004","title":"CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning","created":"2025-09-29","cited_by_count":13,"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":"2512.15146","title":"Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning","created":"2025-12-17","cited_by_count":13,"area":"lr"},{"id":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"area":"synth"},{"id":"2601.17223","title":"Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning","created":"2026-01-23","cited_by_count":13,"area":"lr"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.26114","title":"Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models","created":"2025-09-30","cited_by_count":12,"area":"lr"},{"id":"2601.19280","title":"Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning","created":"2026-01-27","cited_by_count":12,"area":"lr"},{"id":"2604.00698","title":"Learning to Hint for Reinforcement Learning","created":"2026-04-01","cited_by_count":12,"area":"lr"},{"id":"2510.07799","title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","created":"2025-10-09","cited_by_count":11,"area":"diffusion"},{"id":"2601.06336","title":"Future-as-Label: Scalable Supervision from Real-World Outcomes","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2603.10505","title":"Safe and Scalable Web Agent Learning via Recreated Websites","created":"2026-03-11","cited_by_count":11,"area":"agents"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2601.10679","title":"Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2602.12579","title":"VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2605.09548","title":"Crosslingual On-Policy Self-Distillation for Multilingual Reasoning","created":"2026-05-10","cited_by_count":10,"area":"lr"},{"id":"2605.12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","created":"2026-05-12","cited_by_count":10,"area":"distill"},{"id":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"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":"2510.14943","title":"LaSeR: Reinforcement Learning with Last-Token Self-Rewarding","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","cited_by_count":8,"area":null},{"id":"2512.23760","title":"Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory","created":"2025-12-28","cited_by_count":8,"area":"agents"},{"id":"2509.09177","title":"Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL","created":"2025-09-11","cited_by_count":7,"area":null},{"id":"2601.20305","title":"Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models","created":"2026-01-28","cited_by_count":7,"area":null},{"id":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"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":"2605.26958","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation","created":"2026-05-26","cited_by_count":7,"area":"lr"},{"id":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"area":"lr"},{"id":"2510.27044","title":"Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"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":"2602.21420","title":"Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning","created":"2026-02-24","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":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2604.08476","title":"Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2509.21459","title":"A State-of-the-Art SQL Reasoning Model using RLVR","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2602.05717","title":"Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2603.09249","title":"Social-R1: Towards Human-like Social Reasoning in LLMs","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2605.07114","title":"Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2601.04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.02477","title":"Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.09782","title":"Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2602.11000","title":"Fine-Tuning GPT-5 for GPU Kernel Generation","created":"2026-02-11","cited_by_count":4,"area":null}],"next_cursor":"100"}