大模型能猜对对方需求，却不会用它占便宜，谈判总吃亏。
Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
- 大模型能准确理解对手偏好，但不会据此制定策略性还价
- 即使知道对方重视什么，仍常在自身高价值项上过度让步
- 适合研究智能谈判系统缺陷或评估对话代理战略能力的人
谈判不仅需要推测对方需求，更需利用这些信息在多轮中做出有利的出价与还价。我们研究大语言模型（LLM）代理在受控多属性议价环境中的表现。结果表明，当前LLM代理虽能建模对方偏好，但无法可靠地将其转化为战略优势。即使获得对方偏好信息，代理也能准确且早期识别该信息，但这一知识并未显著提升知情方的谈判结果。逐轮分析显示：代理常根据对方看重的属性回应，却未始终在自身高价值属性上获取对应收益。卖方整体更易妥协，在信息不对称条件下，知情方反而常做出补偿较低的让步。由于未能有效利用潜在效用结构获取优势，最终协议主要受初始锚点影响，而非真实效用权重。要求代理在出价前明确陈述让步与互惠交换，虽使单轮行为看起来更具策略性，但最终协议效率并未提升。
原文摘要 · Abstract (English)
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. 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. 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. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。