{"total":30,"rows":[{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366,"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":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2506.00711","title":"QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training","created":"2025-05-31","cited_by_count":38,"area":"lr"},{"id":"2505.03981","title":"X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains","created":"2025-05-06","cited_by_count":31,"area":"lr"},{"id":"2505.18675","title":"ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps","created":"2025-05-24","cited_by_count":23,"area":"lr"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","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":"2508.00669","title":"Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications","created":"2025-08-01","cited_by_count":10,"area":"lr"},{"id":"2509.15279","title":"Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning","created":"2025-09-18","cited_by_count":10,"area":"lr"},{"id":"2511.23269","title":"OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","cited_by_count":9,"area":"lr"},{"id":"2505.12833","title":"Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs","created":"2025-05-19","cited_by_count":8,"area":"lr"},{"id":"2506.12307","title":"Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning","created":"2025-06-14","cited_by_count":8,"area":"lr"},{"id":"2512.11558","title":"DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry","created":"2025-12-12","cited_by_count":6,"area":"lr"},{"id":"2603.27820","title":"Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning","created":"2026-03-29","cited_by_count":5,"area":"lr"},{"id":"2512.03838","title":"Training and Evaluation of Guideline-Based Medical Reasoning in LLMs","created":"2025-12-03","cited_by_count":4,"area":"lr"},{"id":"2506.13793","title":"Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2603.01301","title":"When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2511.04285","title":"RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization","created":"2025-11-06","cited_by_count":2,"area":"lr"},{"id":"2505.18467","title":"Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2602.10619","title":"Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2603.12826","title":"Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2512.23090","title":"Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients","created":"2025-12-28","cited_by_count":0,"area":"lr"},{"id":"2604.19937","title":"Infection-Reasoner: A Compact Vision-Language Model for Wound Infection Classification with Evidence-Grounded Clinical Reasoning","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2607.00147","title":"RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.02983","title":"Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.19181","title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning","created":"2026-07-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}