让大模型学会用自然语言讨价还价，提升谈判策略能力。
AgreeMate: Teaching LLMs to Haggle
- 采用模块化架构，让大模型通过自然语言进行价格博弈。
- 结合提示工程与思维链，谈判成功率显著提升。
- 适合对智能对话与商业策略感兴趣的开发者和研究者。
我们提出 AgreeMate，一种训练大语言模型（LLMs）进行战略价格谈判的框架。在该框架中，两名代理（买家或卖家）使用自然语言对商品进行粗粒度动作的讨价还价。具体而言，我们将最新进展应用于解耦（模块化）的谈判架构，评估大模型作为代理的表现。结果表明，通过提示工程、微调和思维链提示，模型性能在新定义的指标下得到显著提升。我们还通过注意力探针分析模型在谈判过程中对词元间语义关系的关注机制。
原文摘要 · Abstract (English)
We introduce AgreeMate, a framework for training Large Language Models (LLMs) to perform strategic price negotiations through natural language. We apply recent advances to a negotiation setting where two agents (i.e. buyer or seller) use natural language to bargain on goods using coarse actions. Specifically, we present the performance of Large Language Models when used as agents within a decoupled (modular) bargaining architecture. We demonstrate that using prompt engineering, fine-tuning, and chain-of-thought prompting enhances model performance, as defined by novel metrics. We use attention probing to show model attention to semantic relationships between tokens during negotiations.
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。