研究人员开发了一个名为BOND（贝叶斯对手信念谈判提炼）的新框架，以使谈判代理更具可审计性。该系统使用大型语言模型在对话中推断和更新关于对手价值的信念。然后，一个较小的、提炼后的模型利用这些信念来做出决策，并可以输出归一化的后验信念，在CaSiNo谈判数据集上表现优于现有的最先进方法。 AI
影响 引入了一种使基于LLM的谈判代理更透明和可审计的方法。
排序理由 这是一篇详细介绍AI谈判代理新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.04507v1 Announce Type: new Abstract: Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but their opponen…
Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but their opponent beliefs are usually implicit and difficult to …
Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but their opponent beliefs are usually implicit and difficult to …