18万次AI谈判实验证明：温暖沟通更易达成协议，技术策略影响显著。
Advancing AI Negotiations: A Large-Scale Autonomous Negotiation Competition
- 通过大规模自动化谈判实验，测试不同提示策略对AI代理表现的影响。
- 温暖语气显著提升成交率与双方收益，而冗长对话易导致谈判破裂。
- 揭示了链式思考、提示注入等AI特有策略，需建立新理论框架。
我们举办了国际人工智能谈判竞赛，参与者设计并优化了AI谈判代理的提示词。随后，在多种具有不同特征和目标的情境中，推动了超过18万次的代理间谈判。研究发现，尽管是AI-AI交互，人类谈判理论的核心原则依然关键。令人意外的是，传统上属于人际互动的“温暖”特质，始终与各项关键绩效指标的优异表现相关。占据主导地位的代理在价值索取方面尤为有效。分析还揭示了现有理论无法完全解释的AI-AI谈判独特动态，包括链式思维推理和提示注入等技术策略。通过对全部谈判记录进行自然语言处理，我们发现积极表达、感恩和提问（体现温暖）与达成协议、客观及主观价值高度相关；而对话长度（体现主导性）则与谈判僵局强相关。结果表明，亟需建立融合经典谈判理论与AI特有机制的新谈判理论，以更好地理解自主谈判行为并优化代理性能。
原文摘要 · Abstract (English)
We conducted an International AI Negotiation Competition in which participants designed and refined prompts for AI negotiation agents. We then facilitated over 180,000 negotiations between these agents across multiple scenarios with diverse characteristics and objectives. Our findings revealed that principles from human negotiation theory remain crucial even in AI-AI contexts. Surprisingly, warmth -- a traditionally human relationship-building trait -- was consistently associated with superior outcomes across all key performance metrics. Dominant agents, meanwhile, were especially effective at claiming value. Our analysis also revealed unique dynamics in AI-AI negotiations not fully explained by existing theory, including AI-specific technical strategies like chain-of-thought reasoning and prompt injection. When we applied natural language processing (NLP) methods to the full transcripts of all negotiations, we found positivity, gratitude, and question-asking (associated with warmth) were strongly associated with reaching deals as well as objective and subjective value, whereas conversation lengths (associated with dominance) were strongly associated with impasses. The results suggest the need to establish a new theory of AI negotiation, which integrates classic negotiation theory with AI-specific negotiation theories to better understand autonomous negotiations and optimize agent performance.
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。