5 papers
Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning
Ruosong Ye, Caiqi Zhang, Jiahao Li +9
Large Language Model (LLM) based Multi-Agent Debate (MAD) is one of the most effective test time scaling techniques. Through multi-round communication, agents complement each other…
Scaling Automatic Research Agents via World Models
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng +8
Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability t…
One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles
Zhichen Zeng, Huiyuan Chen, Jingru Cheng +7
Specializing Large Language Models (LLMs) toward distinct abilities underpins successes ranging from personalized assistants to multi-agent systems (MAS). Single-agent paradigms re…
Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation
Cedar Site Bai, Zhenyu Liao, Duanshun Li +6
Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and natural dialogu…
Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders
Ge Zhang, Jingru Cheng, Huiyuan Chen
Large language models (LLMs) used as listwise rerankers in recommendation systems suffer from position bias when serializing candidate sets into prompts. We show this order sensiti…