或许与我成交：情绪在多智能体谈判中的作用
Deal Me Maybe: The Role of Emotions in Multi-Agent Negotiation
浏览论文内容
中文总结 AI 辅助
该研究探讨提示条件下的情绪对LLM多智能体价格谈判的影响，发现愤怒买方成交率极低，快乐买方成交率最高但价格较差，情绪效应具有角色依赖性，引发商业中情绪条件智能体的担忧。
中文摘要 AI 辅助
谈判是大型语言模型（LLM）智能体需要完成的高要求社交任务，涉及策略推理、说服和人际适应。然而现有基准通常将智能体视为情绪中立的，忽略了人类议价行为的关键驱动因素。我们研究提示条件下的情绪如何影响基于LLM的价格谈判。在一个受控框架中，买方和卖方智能体被独立分配六种情绪状态之一，并在两种预算条件下就350种真实消费品进行谈判。在36种情绪配对设置和五种广泛使用的LLM中，我们发现情绪强烈影响谈判结果：愤怒的买方几乎无法达成协议（成交率0.39%），而快乐的买方达成协议的频率最高（28.91%），但获得的价格比恐惧的买方更差。情绪效应具有角色依赖性：买方情绪主要驱动接受和拒绝行为，而卖方情绪则影响让步动态。这些效应不仅影响语言，还影响终止行为和价格轨迹，引发了对商业中情绪条件智能体的担忧。
英文摘要
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.
