Reinforcement Learning

Self-Augmented Preference Alignment for Sycophancy Reduction in LLMs EMNLP 2025 SELFGOAL: Your Language Agents Already Know How to Achieve High-level Goals NAACL 2025 SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation ACL 2025 Sequence-level Large Language Model Training with Contrastive Preference Optimization NAACL 2025 Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? ACL 2025 ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning ICCV 2025 Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL ACL 2025 SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis EMNLP 2025 SLRL: Semi-Supervised Local Community Detection Based on Reinforcement Learning AAAI 2025 SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction EMNLP 2025 Solving Robust Markov Decision Processes: Generic, Reliable, Efficient AAAI 2025 SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch AAAI 2025 SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models EMNLP 2025 Sources of Disagreement in Data for LLM Instruction Tuning COLING 2025 Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning ACL 2025 Sparse Rewards Can Self-Train Dialogue Agents ACL 2025 Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively ACL 2025 Spontaneous Giving and Calculated Greed in Language Models EMNLP 2025 SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin EMNLP 2025 STACKFEED: Structured Textual Actor-Critic Knowledge base editing with FEEDback EMNLP 2025 START: Self-taught Reasoner with Tools EMNLP 2025 Statistical field theory for Markov decision processes under uncertainty JMLR 2025 Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory AISTATS 2025 Steering LLM Reasoning Through Bias-Only Adaptation EMNLP 2025 Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction ICLR 2025