Reinforcement Learning

Uncertainty-Aware Iterative Preference Optimization for Enhanced LLM Reasoning ACL 2025 Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL ACL 2025 Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality AISTATS 2025 Understanding Reference Policies in Direct Preference Optimization NAACL 2025 Understand the Implication: Learning to Think for Pragmatic Understanding ACL 2025 Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference EMNLP 2025 Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems AAAI 2025 Using LLMs to improve RL policies in personalized health adaptive interventions NAACL 2025 Variational Adversarial Training Towards Policies with Improved Robustness AISTATS 2025 VideoDPO: Omni-Preference Alignment for Video Diffusion Generation CVPR 2025 VisionArena: 230k Real World User-VLM Conversations with Preference Labels CVPR 2025 Visual-RFT: Visual Reinforcement Fine-Tuning ICCV 2025 Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration AAAI 2025 WAVE: Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning L4DC 2025 WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning EMNLP 2025 What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning AAAI 2025 When2Call: When (not) to Call Tools NAACL 2025 When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning EMNLP 2025 When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning EMNLP 2025 Why Does ChatGPT “Delve” So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models COLING 2025 YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering ACL 2025 Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference ICLR 2025 B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis ICLR 2024 A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective NeurIPS 2024 A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent AISTATS 2024