情绪影响大模型谈判结果，愤怒买家几乎不成交
Deal Me Maybe: The Role of Emotions in Multi-Agent Negotiation
- 给大模型设定六种情绪状态，模拟买卖双方谈判
- 愤怒买家成交率仅0.39%，开心买家达28.91%但价格吃亏
- 情绪影响决策和议价轨迹，适合研究人机交互与商业应用
谈判是大型语言模型代理的一项复杂社交任务，需要策略推理、说服力和人际适应。然而现有基准常将代理视为情绪中立，忽略了人类谈判行为的关键驱动因素。本文研究提示词条件下的情绪如何影响基于LLM的定价谈判。在受控框架下，买方和卖方代理被独立赋予六种情绪状态，针对350种真实消费品在两种预算条件下进行谈判。涵盖36种情绪组合及五种主流LLM，结果表明情绪显著影响谈判结果：愤怒买家几乎不达成协议（0.39%成交率），而开心买家成交率最高（28.91%），但获得的价格不如害怕的买家。情绪效应具有角色依赖性——买方情绪主要影响接受或拒绝，卖方情绪则主导让步行为。这些影响不仅体现在语言上，还作用于终止行为和价格走势，引发对情绪驱动代理在商业场景中应用的担忧。
原文摘要 · Abstract (English)
Negotiation is a demanding social task for LLM agents, requiring strategic reasoning, persuasion, and interpersonal adaptation. Yet existing benchmarks often treat agents as emotionally neutral, overlooking a key driver of human bargaining behavior. We study how prompt-conditioned emotions affect LLM-based price negotiation. In a controlled framework, buyer and seller agents are independently assigned one of six emotional states and negotiate over 350 real consumer products under two budget conditions. Across 36 emotion-pair settings and five widely used LLMs, we find that emotions strongly shape outcomes. Angry buyers almost never reach agreement (0.39% deal rate), while happy buyers agree most often (28.91%), but obtain worse prices than fearful buyers. Emotion effects are role-dependent: buyer emotion mainly drives acceptance and rejection, whereas seller emotion shapes concession dynamics. These effects influence not only language, but also termination behavior and price trajectories, raising concerns for emotion-conditioned agents in commerce.
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。