{"total":62,"rows":[{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"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":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"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":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"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":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2510.07242","title":"Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense","created":"2025-10-08","cited_by_count":20,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"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":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2509.24945","title":"MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2510.06534","title":"Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them","created":"2025-10-08","cited_by_count":7,"area":"lr"},{"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":"2509.24375","title":"Reinforcement Mid-Training","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2601.13761","title":"DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution","created":"2026-01-20","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2509.26226","title":"Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2509.20186","title":"Thinking Augmented Pre-training","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2509.21124","title":"Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2511.04285","title":"RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization","created":"2025-11-06","cited_by_count":2,"area":"lr"},{"id":"2601.03111","title":"One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2603.00889","title":"CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning","created":"2026-03-01","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":"2605.28008","title":"Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.04889","title":"GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2603.21719","title":"Probing How Scalable Table Data Enhances General Long-Context Reasoning","created":"2026-03-23","cited_by_count":1,"area":"lr"},{"id":"2605.20066","title":"Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.03608","title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2609.36641","title":"Inducing Process Supervision from Outcome-Only Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2601.04731","title":"Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models","created":"2026-01-08","cited_by_count":0,"area":"lr"},{"id":"2601.14599","title":"Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2602.02979","title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.11748","title":"Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2603.22352","title":"WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement","created":"2026-03-22","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":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.26862","title":"ReCo: Reweighting GRPO Against Distributional Concentration","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.25936","title":"One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.26053","title":"$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.01532","title":"Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.37868","title":"Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00903","title":"Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04299","title":"Questioning the Questions: Sustaining Self-Evolution in Reasoning Models","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.06851","title":"Base Models Can Reason By Taking a Cue From Training Data","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}