3 papers
cs.LG2026
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…
cs.MA2026
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…
cs.IR2026
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…