Reinforcement Learning

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models ICLR 2025 T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback ACL 2025 Table-R1: Inference-Time Scaling for Table Reasoning Tasks EMNLP 2025 TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning ACL 2025 TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making EMNLP 2025 Teaching Language Models To Gather Information Proactively EMNLP 2025 Teaching Models to Improve on Tape AAAI 2025 Terminology-Constrained Translation from Monolingual Data Using GRPO EMNLP 2025 Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization EMNLP 2025 The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards AAAI 2025 The Impact of Language Mixing on Bilingual LLM Reasoning EMNLP 2025 Theorem Prover as a Judge for Synthetic Data Generation ACL 2025 Thinking Out Loud: Do Reasoning Models Know When They’re Right? EMNLP 2025 TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use EMNLP 2025 To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization ACL 2025 Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models IJCAI 2025 Token-level Proximal Policy Optimization for Query Generation EMNLP 2025 Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards CVPR 2025 Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning AAAI 2025 Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2025 Towards General-Purpose Model-Free Reinforcement Learning ICLR 2025 Training Language Models to Critique With Multi-agent Feedback EMNLP 2025 Training Language Model to Critique for Better Refinement ACL 2025 TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation EMNLP 2025 Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL ACL 2025