18 papers
Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning
Yuting Liu, Wei Wu, Jianzhe Zhao +1
Natural language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain information irrelevant to a part…
PCTD: Preference-Guided Counterfactual Task Decomposition for Agent Tool Retrieval
Chu Zhao, Lei Tang, Minghang Li +5
Task decomposition aims to transform ambiguous instructions into executable atomic subtasks, thereby guiding high-precision tool retrieval. However, our analysis reveals that direc…
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
Chu Zhao, Enneng Yang, Jianzhe Zhao +1
Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference al…
ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
Chu Zhao, Enneng Yang, Yuting Liu +2
Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduc…
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Weiyu Ma, Yongcheng Zeng, Yan Song +4
Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO,…
Hard Negative Sampling via Large Language Models for Recommendation
Chu Zhao, Enneng Yang, Yuting Liu +2
Hard negative sampling improves recommendation performance by accelerating convergence and sharpening the decision boundary. However, most existing methods rely on heuristic strate…