Reinforcement Learning

S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning ACL 2025 Sample Efficient Alignment Learning With Episodic Control EMNLP 2025 Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation AAAI 2025 Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments CVPR 2025 SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models EMNLP 2025 SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models EMNLP 2025 SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories CVPR 2025 Selective Preference Optimization via Token-Level Reward Function Estimation EMNLP 2025 Self-Correcting Code Generation Using Small Language Models EMNLP 2025 Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models ACL 2025 Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback AAAI 2025 Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task EMNLP 2025 SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks AAAI 2025 Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning EMNLP 2025 Solving hidden monotone variational inequalities with surrogate losses ICLR 2025 SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models EMNLP 2025 Sparse Rewards Can Self-Train Dialogue Agents ACL 2025 SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning EMNLP 2025 SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin EMNLP 2025 SQUREL at TSAR 2025 Shared Task CEFR-Controlled Text Simplification with Prompting and Reinforcement Fine-Tuning EMNLP 2025 Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation ICLR 2025 Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning ICLR 2025 STACKFEED: Structured Textual Actor-Critic Knowledge base editing with FEEDback EMNLP 2025 STREAQ: Selective Tiered Routing for Effective and Affordable Contact Center Quality Assurance EMNLP 2025 Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing ACL 2025