Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation

Summary

Researchers tested whether LLM negotiation agents can build useful trust estimates from prior interactions in repeated multi-party, multi-issue games where one participant covertly tries to block agreement. Trust-aware agents identified the adversary within a few games, but accurate trust did not consistently yield better agreements. Explicitly guiding agents to use trust raised agreement rates by up to 23 percentage points.