{"total":29,"rows":[{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"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":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143,"area":"lr"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2402.19450","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","created":"2024-02-29","cited_by_count":79,"area":"lr"},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53,"area":"lr"},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39,"area":"lr"},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16,"area":"lr"},{"id":"2509.25004","title":"CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning","created":"2025-09-29","cited_by_count":13,"area":"lr"},{"id":"2309.08589","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","created":"2023-09-15","cited_by_count":8,"area":"lr"},{"id":"2410.21526","title":"Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification","created":"2024-10-28","cited_by_count":6,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2601.06160","title":"Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2509.16551","title":"Rethinking the Role of Text Complexity in Language Model Pretraining","created":"2025-09-20","cited_by_count":2,"area":"lr"},{"id":"2601.06373","title":"DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation","created":"2026-01-10","cited_by_count":2,"area":"lr"},{"id":"2601.06786","title":"EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs","created":"2026-01-11","cited_by_count":2,"area":"lr"},{"id":"2603.13309","title":"Preventing Curriculum Collapse in Self-Evolving Reasoning Systems","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2604.11188","title":"MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2505.20313","title":"Reasoning in Neurosymbolic AI","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2603.18361","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2604.26653","title":"AgentSim: A Platform for Verifiable Agent-Trace Simulation","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2412.04645","title":"REL: Working out is all you need","created":"2024-12-05","cited_by_count":0,"area":"lr"},{"id":"2507.00054","title":"Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation","created":"2025-06-25","cited_by_count":0,"area":"lr"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2602.08344","title":"OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2605.11666","title":"Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling","created":"2026-05-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}