{"total":36,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205,"area":"lr"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"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":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2404.12253","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","created":"2024-04-18","cited_by_count":125,"area":"lr"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2408.13890","title":"Making Large Language Models Better Planners with Reasoning-Decision Alignment","created":"2024-08-25","cited_by_count":52,"area":"lr"},{"id":"2407.16574","title":"TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback","created":"2024-07-23","cited_by_count":43,"area":"lr"},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35,"area":"lr"},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2402.11452","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","created":"2024-02-18","cited_by_count":24,"area":"lr"},{"id":"2601.20218","title":"DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment","created":"2026-01-28","cited_by_count":21,"area":"lr"},{"id":"2312.14591","title":"Reasons to Reject? Aligning Language Models with Judgments","created":"2023-12-22","cited_by_count":15,"area":"lr"},{"id":"2503.08525","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","created":"2025-03-11","cited_by_count":14,"area":"lr"},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2508.02344","title":"Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2512.04601","title":"Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space","created":"2025-12-04","cited_by_count":8,"area":"lr"},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2502.16944","title":"Pretrain Value, Not Reward: Decoupled Value Policy Optimization","created":"2025-02-24","cited_by_count":6,"area":"lr"},{"id":"2512.01457","title":"Zero-Overhead Introspection for Adaptive Test-Time Compute","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2603.23414","title":"SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling","created":"2026-03-24","cited_by_count":6,"area":"lr"},{"id":"2401.13246","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","created":"2024-01-24","cited_by_count":3,"area":"lr"},{"id":"2410.17088","title":"Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning","created":"2024-10-22","cited_by_count":3,"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":"2603.13628","title":"Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models","created":"2026-03-13","cited_by_count":2,"area":"lr"},{"id":"2503.17136","title":"CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization","created":"2025-03-21","cited_by_count":1,"area":"lr"},{"id":"2604.08926","title":"Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2602.03640","title":"Tutorial on Reasoning for IR & IR for Reasoning","created":"2026-02-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}