Reinforcement Learning

Optimizing Decomposition for Optimal Claim Verification ACL 2025 Optimizing Heat Alert Issuance with Reinforcement Learning AAAI 2025 Optimizing Return Distributions with Distributional Dynamic Programming JMLR 2025 Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs AISTATS 2025 Pareto Prompt Optimization ICLR 2025 PaSa: An LLM Agent for Comprehensive Academic Paper Search ACL 2025 Personalized Preference Fine-tuning of Diffusion Models CVPR 2025 PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment EMNLP 2025 PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025 Positive Experience Reflection for Agents in Interactive Text Environments ACL 2025 Predicate-Guided Generation for Mathematical Reasoning EMNLP 2025 Prediction-Based Adaptive Variable Ordering Heuristics for Constraint Satisfaction Problems AAAI 2025 Primal-Dual Spectral Representation for Off-policy Evaluation AISTATS 2025 Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF JMLR 2025 Prior Prompt Engineering for Reinforcement Fine-Tuning EMNLP 2025 PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models ACL 2025 Proactive Guidance of Multi-Turn Conversation in Industrial Search ACL 2025 Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching L4DC 2025 Probabilistic Shielding for Safe Reinforcement Learning AAAI 2025 Procedural Environment Generation for Tool-Use Agents EMNLP 2025 Process-Supervised Reinforcement Learning for Code Generation EMNLP 2025 Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning CVPR 2025 PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning EMNLP 2025 Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis AISTATS 2025 R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning EMNLP 2025