Skip to content
AI情报2026年8月17日AI情报
文章

Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes

When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversation terminates without achieving either agent's stated objective. This paper asks whether a control-theore...

Frontier 编辑部来源: arXiv
01

来源简报

Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes: When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversation terminates without achieving either agent's stated objective. This paper asks whether a control-theore...