5 papers
Learning to Steer LLM Agents and Multi-Agent Systems
Leyang Shen, Yaxin Gong, Yang Zhang +7
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these system…
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Yaxin Gong, Gangyi Zhang, Chongming Gao +7
Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answ…
Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation
Yaxin Gong, Chongming Gao, Chenxiao Fan +6
Large language models (LLMs) have spurred interest in agent-based recommender systems, yet most agentic approaches remain user-centric: items stay passive entities whose exposure i…
Uncertainty-aware Generative Recommendation
Chenxiao Fan, Chongming Gao, Yaxin Gong +3
Generative Recommendation has emerged as a transformative paradigm, reformulating recommendation as an end-to-end autoregressive sequence generation task. Despite its promise, exis…
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…