{"total":23,"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":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2510.01265","title":"RLP: Reinforcement as a Pretraining Objective","created":"2025-09-26","cited_by_count":25,"area":"lr"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2510.01304","title":"Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models","created":"2025-10-01","cited_by_count":11,"area":"lr"},{"id":"2602.03979","title":"Likelihood-Based Reward Designs for General LLM Reasoning","created":"2026-02-03","cited_by_count":7,"area":"lr"},{"id":"2605.19444","title":"Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting","created":"2026-05-19","cited_by_count":7,"area":"lr"},{"id":"2509.24375","title":"Reinforcement Mid-Training","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2509.20186","title":"Thinking Augmented Pre-training","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2512.12633","title":"DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model","created":"2025-12-14","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2506.13502","title":"BOW: Training Language Models to Reason Over Plausible Next Words","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2510.13879","title":"Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2511.13726","title":"Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2512.22955","title":"Diversity or Precision? A Deep Dive into Next Token Prediction","created":"2025-12-28","cited_by_count":1,"area":"lr"},{"id":"2602.22765","title":"Towards Better RL Training Data Utilization via Second-Order Rollout","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2603.09221","title":"Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2602.02979","title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2608.23256","title":"Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.32791","title":"$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}