{"total":54,"rows":[{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2310.05746","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","created":"2023-10-09","cited_by_count":78,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2403.06447","title":"CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation","created":"2024-03-11","cited_by_count":44,"area":"lr"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2401.09334","title":"Large Language Models Are Neurosymbolic Reasoners","created":"2024-01-17","cited_by_count":31,"area":"lr"},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31,"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":"2505.08364","title":"Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation","created":"2025-05-13","cited_by_count":20,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18,"area":"lr"},{"id":"2211.15864","title":"Peano: Learning Formal Mathematical Reasoning","created":"2022-11-29","cited_by_count":15,"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":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2606.01281","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","created":"2026-05-31","cited_by_count":9,"area":"lr"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2606.01039","title":"OPD+: Rethinking the Advantage Design for On-Policy Distillation","created":"2026-05-31","cited_by_count":8,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2508.21365","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","created":"2025-08-29","cited_by_count":7,"area":"lr"},{"id":"2409.10188","title":"Enhancing RL Safety with Counterfactual LLM Reasoning","created":"2024-09-16","cited_by_count":6,"area":"lr"},{"id":"2408.01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","created":"2024-08-04","cited_by_count":4,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2603.16157","title":"DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2211.01994","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","created":"2022-11-03","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":"2506.09080","title":"FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making","created":"2025-06-10","cited_by_count":3,"area":"lr"},{"id":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2408.14855","title":"Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL","created":"2024-08-27","cited_by_count":2,"area":"lr"},{"id":"2505.19815","title":"Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective","created":"2025-05-26","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":"2410.13018","title":"Learning Representations for Reasoning: Generalizing Across Diverse Structures","created":"2024-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.14686","title":"IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2406.19500","title":"Knowledge acquisition for dialogue agents using reinforcement learning on graph representations","created":"2024-06-27","cited_by_count":0,"area":"lr"},{"id":"2407.04858","title":"Question Answering with Texts and Tables through Deep Reinforcement Learning","created":"2024-07-05","cited_by_count":0,"area":"lr"},{"id":"2410.08334","title":"Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning","created":"2024-10-10","cited_by_count":0,"area":"lr"},{"id":"2505.11893","title":"RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving","created":"2025-05-17","cited_by_count":0,"area":"lr"},{"id":"2507.08705","title":"elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings","created":"2025-07-11","cited_by_count":0,"area":"lr"},{"id":"2507.13142","title":"From Roots to Rewards: Dynamic Tree Reasoning with Reinforcement Learning","created":"2025-07-17","cited_by_count":0,"area":"lr"},{"id":"2510.21306","title":"PARL: Prompt-based Agents for Reinforcement Learning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2602.01915","title":"VLM-Guided Experience Replay","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2603.23355","title":"Off-Policy Value-Based Reinforcement Learning for Large Language Models","created":"2026-03-24","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":"2605.22195","title":"Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.05174","title":"Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2608.26147","title":"CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}