自动化却充满风险的游戏：消费者市场中代理间谈判与交易的建模

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets

May 29, 2025

作者: Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, Jiaxin Pei

cs.AI

摘要

AI代理在面向消费者的应用中日益普及，用于协助完成诸如产品搜索、议价及交易执行等任务。本文探讨了一种未来场景，即消费者与商家均授权AI代理全自动化处理议价与交易。我们旨在解答两个关键问题：(1) 不同的大型语言模型（LLM）代理在为用户争取有利交易条件的能力上是否存在差异？(2) 在消费市场中，完全依赖AI代理进行交易自动化会带来哪些风险？为解答这些问题，我们构建了一个实验框架，评估多种LLM代理在真实世界议价与交易情境下的表现。研究发现，AI中介的交易本质上是一场不平衡的游戏——不同代理为其用户达成的结果存在显著差异。此外，LLM中的行为异常可能导致消费者与商家双方遭受财务损失，如过度消费或接受不合理交易。这些结果强调，尽管自动化能提升效率，但也引入了重大风险。用户在将商业决策委托给AI代理时，应保持谨慎。

English

AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a future scenario where both consumers and merchants authorize AI agents to fully automate negotiations and transactions. We aim to answer two key questions: (1) Do different LLM agents vary in their ability to secure favorable deals for users? (2) What risks arise from fully automating deal-making with AI agents in consumer markets? To address these questions, we develop an experimental framework that evaluates the performance of various LLM agents in real-world negotiation and transaction settings. Our findings reveal that AI-mediated deal-making is an inherently imbalanced game -- different agents achieve significantly different outcomes for their users. Moreover, behavioral anomalies in LLMs can result in financial losses for both consumers and merchants, such as overspending or accepting unreasonable deals. These results underscore that while automation can improve efficiency, it also introduces substantial risks. Users should exercise caution when delegating business decisions to AI agents.