{"total":20,"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":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2601.10712","title":"MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2602.09953","title":"ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning","created":"2026-02-10","cited_by_count":9,"area":"lr"},{"id":"2512.07436","title":"LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services","created":"2025-12-08","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2510.16416","title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","created":"2025-10-18","cited_by_count":7,"area":"lr"},{"id":"2512.19126","title":"AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards","created":"2025-12-22","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2509.25827","title":"Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2512.08980","title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","created":"2025-12-05","cited_by_count":4,"area":"lr"},{"id":"2606.05784","title":"TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.18936","title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.03503","title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2609.21492","title":"LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers","created":"2026-09-18","cited_by_count":1,"area":"lr"},{"id":"2609.32482","title":"From Outcomes to Strategies: Learning Strategy Utility for Mathematical Reasoning","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}