{"total":31,"rows":[{"id":"2507.14111","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","created":"2025-07-18","cited_by_count":61,"area":"lr"},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2502.05078","title":"Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures","created":"2025-02-07","cited_by_count":16,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2509.16889","title":"Can GRPO Boost Complex Multimodal Table Understanding?","created":"2025-09-21","cited_by_count":10,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2508.04848","title":"Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning","created":"2025-08-06","cited_by_count":7,"area":"lr"},{"id":"2508.05118","title":"Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function Calling","created":"2025-08-07","cited_by_count":7,"area":"lr"},{"id":"2603.07197","title":"$\\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving","created":"2026-03-07","cited_by_count":6,"area":"lr"},{"id":"2603.12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2602.04326","title":"From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2510.12264","title":"Reducing Belief Deviation in Reinforcement Learning for Active Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2511.13885","title":"Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search","created":"2025-11-17","cited_by_count":4,"area":"lr"},{"id":"2608.18855","title":"Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval","created":"2026-08-19","cited_by_count":4,"area":"lr"},{"id":"2604.07851","title":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","created":"2026-04-09","cited_by_count":3,"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":"2507.15586","title":"Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation","created":"2025-07-21","cited_by_count":1,"area":"lr"},{"id":"2509.03537","title":"AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models","created":"2025-08-27","cited_by_count":1,"area":"lr"},{"id":"2601.05633","title":"GIFT: Games as Informal Training for Generalizable LLMs","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2602.05472","title":"ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2608.08623","title":"MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning","created":"2026-08-09","cited_by_count":1,"area":"lr"},{"id":"2506.02726","title":"RACE-Align: Retrieval-Augmented and Chain-of-Thought Enhanced Preference Alignment for Large Language Models","created":"2025-06-03","cited_by_count":0,"area":"lr"},{"id":"2602.10006","title":"Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning","created":"2026-02-10","cited_by_count":0,"area":"lr"},{"id":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}