{"total":23,"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":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32,"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":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"area":"lr"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2507.07498","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2509.19681","title":"Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2603.29957","title":"Think Anywhere in Code Generation","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.23488","title":"Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.12373","title":"Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2607.21971","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2510.11104","title":"Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2602.01660","title":"CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2609.36820","title":"CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00991","title":"Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.06671","title":"Learning What to Imitate: Entropy-Aware Distribution Mixing","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}