Reinforcement Learning

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning EMNLP 2025 Continual SFT Matches Multimodal RLHF with Negative Supervision CVPR 2025 Continuously evolving rewards in an open-ended environment JMLR 2025 Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs JMLR 2025 ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning EMNLP 2025 Counterfactual Online Learning for Open-Loop Monte-Carlo Planning AAAI 2025 Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization EMNLP 2025 Cross-Validated Off-Policy Evaluation AAAI 2025 CTD4 – a Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics AAAI 2025 CTR-Guided Generative Query Suggestion in Conversational Search EMNLP 2025 CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis ACL 2025 Curiosity-Driven Reinforcement Learning from Human Feedback ACL 2025 Curriculum Direct Preference Optimization for Diffusion and Consistency Models CVPR 2025 Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences ICCV 2025 DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization EMNLP 2025 Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math ACL 2025 DEBATE, TRAIN, EVOLVE: Self‐Evolution of Language Model Reasoning EMNLP 2025 Debiasing Online Preference Learning via Preference Feature Preservation ACL 2025 DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision EMNLP 2025 Decision-Point Guided Safe Policy Improvement AISTATS 2025 Decision SpikeFormer: Spike-Driven Transformer for Decision Making CVPR 2025 DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments EMNLP 2025 Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning AAAI 2025 DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback EMNLP 2025 Detoxifying Large Language Models via the Diversity of Toxic Samples EMNLP 2025