Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators

对手建模并非策略：大语言模型谈判者的局限性

Abstract: Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a controlled multi-attribute bargaining environment.

摘要： 谈判不仅仅需要推断对方的需求，还需要利用这些信息在多轮博弈中提出有利的报价和还价。我们研究了大语言模型（LLM）智能体在受控的多属性议价环境中是否具备这种能力。

We find that current LLM agents can model a counterparty’s preferences, but do not reliably turn that knowledge into strategic bargaining. When given negotiating partner preference information, agents model it accurately and early in their reasoning traces, yet this does not reliably improve outcomes for the informed side.

研究发现，当前的大语言模型智能体能够对对手的偏好进行建模，但无法可靠地将这些知识转化为战略性谈判。当被告知谈判伙伴的偏好信息时，智能体能够在推理过程的早期准确地对其进行建模，但这并不能可靠地改善信息占优方的谈判结果。

Turn-level analyses show why: agents often respond to what they believe the counterparty values, but do not consistently pair those moves with gains on their own high-value attributes. Sellers are more accommodating overall, and in asymmetric-information conditions, the informed side often makes the more weakly compensated concessions.

轮次分析揭示了原因：智能体往往会针对它们认为对手看重的因素做出反应，但却无法始终将这些举动与自身高价值属性的收益挂钩。总体而言，卖方表现得更为迁就；而在信息不对称的情况下，掌握信息的一方往往会做出补偿不足的让步。

Because agents fail to leverage this underlying utility structure for strategic advantage, their final agreements are heavily dictated by surface-level opening anchors rather than actual utility weights. Finally, requiring agents to explicitly state concession-for-reciprocity trades before making an offer makes individual turns look more strategic, but ultimately fails to improve the efficiency of the final agreements.

由于智能体未能利用这种潜在的效用结构来获取战略优势，其最终达成的协议很大程度上受限于表层的开盘锚定效应，而非实际的效用权重。最后，要求智能体在报价前明确说明“以让步换取互惠”的交易，虽然使单轮博弈看起来更具策略性，但最终未能提高达成协议的效率。