{"total":32,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168,"area":"lr"},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123,"area":"lr"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2402.14083","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","created":"2024-02-21","cited_by_count":90,"area":"lr"},{"id":"2302.06706","title":"On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)","created":"2023-02-13","cited_by_count":85,"area":"lr"},{"id":"2501.10074","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","created":"2025-01-17","cited_by_count":62,"area":"lr"},{"id":"2504.15466","title":"Learning Adaptive Parallel Reasoning with Language Models","created":"2025-04-21","cited_by_count":58,"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":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2403.02054","title":"Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism","created":"2024-03-04","cited_by_count":27,"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":"2402.04858","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","created":"2024-02-07","cited_by_count":23,"area":"lr"},{"id":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","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":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2310.05146","title":"Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge","created":"2023-10-08","cited_by_count":11,"area":"lr"},{"id":"2602.03025","title":"RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents","created":"2026-02-03","cited_by_count":11,"area":"lr"},{"id":"2305.17077","title":"Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models","created":"2023-05-26","cited_by_count":10,"area":"lr"},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10,"area":"lr"},{"id":"2404.18988","title":"Markovian Transformers for Informative Language Modeling","created":"2024-04-29","cited_by_count":4,"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":"2501.04424","title":"NSA: Neuro-symbolic ARC Challenge","created":"2025-01-08","cited_by_count":2,"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":"2511.21064","title":"OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2604.16871","title":"GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2606.00240","title":"MindZero: Learning Online Mental Reasoning With Zero Annotations","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.15686","title":"Recurrent Reasoning on Symbolic Puzzles with Sequence Models","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2607.19523","title":"When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play","created":"2026-07-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}