{"total":56,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2512.16649","title":"JustRL: Scaling a 1.5B LLM with a Simple RL Recipe","created":"2025-12-18","cited_by_count":64,"area":null},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"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":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2509.01321","title":"Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward","created":"2025-09-01","cited_by_count":19,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2512.07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning","created":"2025-12-08","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":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","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":"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":"2510.25206","title":"RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models","created":"2025-10-29","cited_by_count":8,"area":"lr"},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2511.17652","title":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","created":"2025-11-20","cited_by_count":5,"area":"lr"},{"id":"2601.07320","title":"Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2511.13885","title":"Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search","created":"2025-11-17","cited_by_count":4,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2605.04077","title":"Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO","created":"2026-04-14","cited_by_count":3,"area":"lr"},{"id":"2605.25604","title":"DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning","created":"2026-05-25","cited_by_count":3,"area":"alignment"},{"id":"2512.10430","title":"T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2512.17206","title":"Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2601.09260","title":"Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2603.16876","title":"Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2604.18963","title":"Distillation Traps and Guards: A Calibration Knob for LLM Distillability","created":"2026-04-21","cited_by_count":1,"area":"distill"},{"id":"2605.21988","title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2608.05541","title":"Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging","created":"2026-08-06","cited_by_count":1,"area":"lr"},{"id":"2609.13443","title":"Learning to Solve Hard Problems in RL for LLMs by Never Giving Up","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2602.11596","title":"MAPLE: Modality-Aware Post-training and Learning Ecosystem","created":"2026-02-12","cited_by_count":0,"area":"mllm"},{"id":"2602.19327","title":"Soft Sequence Policy Optimization","created":"2026-02-22","cited_by_count":0,"area":"lr"},{"id":"2605.27900","title":"Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33970","title":"On the Token Value Inequality in Efficient Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.17771","title":"Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}