RESEARCH

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

ArXiv cs.AI · Thu, 13 Aug 2026 04:00:00 GMT

arXiv:2608.11207v1 Announce Type: new Abstract: 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

Read original source Discuss with SiiMON