{"total":18,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109,"area":"lr"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2510.19842","title":"DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs","created":"2025-10-19","cited_by_count":5,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2511.07372","title":"Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2602.01523","title":"A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2506.10647","title":"Data Shifts Hurt CoT: A Theoretical Study","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2603.00306","title":"When does Chain-of-Thought Help: A Markovian Perspective","created":"2026-02-27","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2602.02909","title":"Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.14404","title":"Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2504.09777","title":"Reasoning without Regret","created":"2025-04-14","cited_by_count":0,"area":"lr"},{"id":"2510.05746","title":"ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems","created":"2025-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}