{"total":17,"rows":[{"id":"2505.21432","title":"Hume: Introducing System-2 Thinking in Visual-Language-Action Model","created":"2025-05-27","cited_by_count":56,"area":"lr"},{"id":"2509.25133","title":"Rethinking Entropy Regularization in Large Reasoning Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2505.07527","title":"Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2310.18127","title":"Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models","created":"2023-10-27","cited_by_count":9,"area":"lr"},{"id":"2511.07581","title":"Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models","created":"2025-11-10","cited_by_count":5,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2511.17171","title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2602.05863","title":"Constrained Group Relative Policy Optimization","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","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":"2505.13921","title":"APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2602.01915","title":"VLM-Guided Experience Replay","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2607.06018","title":"RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.35505","title":"An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.00661","title":"Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}