作者位次 #5/7ACL 2026Findings· Findings of ACL
MDT eam GPT : Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning
Kai Chen · Xinfeng Li · Tianpei Yang · Hewei Wang · Guang Yang · Jing Huo · Yang Gao
摘要
Large language models (LLMs) have shown great potential in multi-disciplinary team (MDT) medical consultations. However, long, multi-round, multi-role interaction trajectories inevitably lead to severe information dilution and context window overload, triggering context collapse which destabilize...