PulseAugur
中
实时 10:18:37
English(EN) Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation

LLM代理在多方谈判中难以建立信任

一项新的研究论文探讨了涉及大型语言模型(LLM)代理的重复多方谈判中信任的挑战。该研究提出了一个框架,代理可以从中形成并使用过去的互动所产生的信任估计。虽然具有信任意识的代理可以识别对手,但研究发现了一个“信任-协议差距”,表明准确的信任估计并不能自动带来更好的谈判结果。该论文提出,明确指导代理在决策中使用信任,可以将协议达成率提高多达23个百分点,这凸显了信任评估和应用方式的关键作用。 AI

影响 强调了在LLM代理中需要明确的信任机制来改善谈判结果。

排序理由 研究论文发表在arXiv上,详细介绍了关于LLM代理行为的发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

LLM代理在多方谈判中难以建立信任

本文如何被排名

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文发表在arXiv上,详细介绍了关于LLM代理行为的发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Amit Sarker, Moumita Choudhury, Saaduddin Mahmud, Shlomo Zilberstein ·

    知晓信任对象并非易事:重复多方LLM谈判中的信任-协议鸿沟

    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-ag…