{"total":18,"rows":[{"id":"2504.05812","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","created":"2025-04-08","cited_by_count":128,"area":"lr"},{"id":"2502.04780","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","created":"2025-02-07","cited_by_count":44,"area":"lr"},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"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":"2510.19363","title":"LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts","created":"2025-10-22","cited_by_count":29,"area":"lr"},{"id":"2502.20790","title":"Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision","created":"2025-02-28","cited_by_count":21,"area":"lr"},{"id":"2502.12583","title":"LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","cited_by_count":12,"area":"lr"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2503.09819","title":"Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval","created":"2025-03-12","cited_by_count":5,"area":"lr"},{"id":"2601.12465","title":"Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2604.21327","title":"Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning","created":"2026-04-23","cited_by_count":3,"area":"lr"},{"id":"2605.31584","title":"LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards","created":"2026-05-29","cited_by_count":2,"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":"2604.07981","title":"A Decomposition Perspective to Long-context Reasoning for LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2606.18831","title":"Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2609.38809","title":"StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}