Back to Home
arXiv AI··Papers & Tech

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

中文摘要

研究指出,LLM智能体在多方谈判中存在信任与协议之间的差距,仅凭信任不足以防止操纵,揭示了其在重复交互中的脆弱性。

English Summary

Research identifies a "trust-agreement gap" in multi-party LLM negotiations, revealing that emergent trust alone cannot prevent manipulation during repeated interactions.

Original Excerpt

arXiv:2610.31971v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly participate in negotiations on behalf of individuals and organizations, yet they remain vulnerable to manipulation, particularly in repeated multi-party interactions. Classical multi-agent systems address this challenge through explicit trust and reputation models, whereas existing work on LLM negotiation largely treats trust as an emergent phenomenon. We investigate whether LLM agents can form useful trust estimates from prior interactions and leverage them to improve future negotiation outcomes. We introduce a repeated, multi-party, multi-issue negotiation framework in which recurring agents participate in a sequence of negotiation games while one participant covertly attempts to prevent agreement. After each game, agents assess their counterparts and maintain pairwise trust estimates that carry over to subsequent negotiations. We compare trust-aware and trust-agnostic agents and analyze how explicit trust influences negotiation outcomes. Our results reveal a \emph{trust--agreement gap}: trust-aware agents can identify the adversary within a few games, but accurate trust estimates do no…