{"total":22,"rows":[{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2505.24105","title":"Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2505.16994","title":"R$^2$ec: Towards Large Recommender Models with Reasoning","created":"2025-05-22","cited_by_count":13,"area":"lr"},{"id":"2504.09627","title":"Slow Thinking for Sequential Recommendation","created":"2025-04-13","cited_by_count":11,"area":"lr"},{"id":"2510.20150","title":"Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning","created":"2025-10-23","cited_by_count":11,"area":"lr"},{"id":"2510.14629","title":"MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2508.07342","title":"PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2601.18664","title":"S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2510.20815","title":"Generative Reasoning Recommendation via LLMs","created":"2025-10-23","cited_by_count":5,"area":"lr"},{"id":"2505.23667","title":"Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2601.04674","title":"PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2506.21638","title":"R1-Ranker: Teaching LLM Rankers to Reason","created":"2025-06-25","cited_by_count":1,"area":"lr"},{"id":"2510.22888","title":"MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2602.12968","title":"RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2604.14051","title":"Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2605.07129","title":"RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2606.01041","title":"ExpWeaver: LLM Agents Learn from Experience via Latent RAG","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.16703","title":"Harmonizing Semantic and Collaborative in LLMs: Reasoning-based Embedding Generator for Sequential Recommendation","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2609.03313","title":"SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2610.17771","title":"Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}