{"total":20,"rows":[{"id":"2505.23614","title":"Inference-time Scaling of Diffusion Models through Classical Search","created":"2025-05-29","cited_by_count":49,"area":"lr"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26,"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":"2304.00776","title":"Chain-of-Thought Predictive Control","created":"2023-04-03","cited_by_count":18,"area":"lr"},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2410.08048","title":"VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers","created":"2024-10-10","cited_by_count":14,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2601.15158","title":"Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2602.07399","title":"VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation","created":"2026-02-07","cited_by_count":5,"area":"lr"},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2410.12568","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2602.05370","title":"Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2606.05263","title":"Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.30627","title":"Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2507.01060","title":"Optimizing Conversational Product Recommendation via Reinforcement Learning","created":"2025-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.27914","title":"Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.30051","title":"Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide","created":"2026-08-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}