Reinforcement Learning

Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving ACL 2025 Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions AAAI 2025 Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning AAAI 2025 LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models EMNLP 2025 LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information ACL 2025 Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models EMNLP 2025 LookAlike: Consistent Distractor Generation in Math MCQs ACL 2025 LORD: Large Models Based Opposite Reward Design for Autonomous Driving WACV 2025 MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models AAAI 2025 Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning NAACL 2025 Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improve Without Labels or Model Updates EMNLP 2025 Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models ACL 2025 MarkovType: A Markov Decision Process Strategy for Non-Invasive Brain-Computer Interfaces Typing Systems AAAI 2025 MasRouter: Learning to Route LLMs for Multi-Agent Systems ACL 2025 MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization ICLR 2025 Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization ACL 2025 Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications L4DC 2025 Misspecified Q-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error ICLR 2025 Mitigating Object Hallucinations via Sentence-Level Early Intervention ICCV 2025 Mixing Inference-time Experts for Enhancing LLM Reasoning EMNLP 2025 Modality-Fair Preference Optimization for Trustworthy MLLM Alignment IJCAI 2025 MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration ICCV 2025 MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification ACL 2025