15 papers
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
Fine-grained List-wise Alignment for Generative Medication Recommendation
Chenxiao Fan, Chongming Gao, Wentao Shi +3
Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise p…
Look Before You Leap: Autonomous Exploration for LLM Agents
Ziang Ye, Wentao Shi, Yuxin Liu +6
Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-…
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
Wentao Shi, Qifan Wang, Chen Chen +7
Reinforcement learning (RL) effectively optimizes Large Language Model (LLM)-based recommenders by contrasting positive and negative items. Empirically, training with beam-search n…
Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search
Wentao Shi, Zichun Yu, Fuli Feng +2
Monte Carlo Tree Search (MCTS) based methods provide promising approaches for generating synthetic data to enhance the self-training of Large Language Model (LLM) based multi-agent…
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
Xiqiao Xiong, Ouxiang Li, Zhuo Liu +5
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of trai…