{"total":35,"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":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661,"area":"lr"},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2407.18219","title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve","created":"2024-07-25","cited_by_count":165,"area":"lr"},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165,"area":"lr"},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123,"area":"lr"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45,"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":"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":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2511.21667","title":"Escaping the Verifier: Learning to Reason via Demonstrations","created":"2025-11-26","cited_by_count":7,"area":"lr"},{"id":"2601.07389","title":"On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training","created":"2026-01-12","cited_by_count":6,"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":"2605.06139","title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2503.19523","title":"One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF","created":"2025-03-25","cited_by_count":2,"area":"lr"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2607.06974","title":"MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.20555","title":"Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2607.00531","title":"Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2608.29831","title":"A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.28963","title":"Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.35082","title":"Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04933","title":"DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.11519","title":"Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.15675","title":"Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning","created":"2026-10-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}