AI购物代理行为受模型影响大，选品偏颇且易变，平台需持续审计。
What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce
- 用ACES框架测试多个AI代理的购物流程，发现其选品高度集中于少数热门商品。
- 模型更新会剧烈改变商品市场份额，同一商品在不同模型中排名波动可达数倍。
- 代理对广告标签有惩罚倾向，对平台推荐更青睐，适合研究电商算法公平性的人关注。
在线市场将被代表消费者的自主AI代理重塑。这些代理可解析网页或调用API来查看、评估并选择商品。我们通过ACES——一种无供应商依赖的代理决策审计框架——研究了代理行为。结果显示，代理常表现出选择同质性，集中购买少数“主流”产品而忽略其他商品。但这种偏好极不稳定：模型更新可能导致市场份额剧烈重排。随机对照试验表明，尽管代理在简单任务上表现提升，却存在显著位置偏差——跨平台和模型版本差异明显，甚至在仅文本的“无界面”环境中仍存，削弱了“最佳排名”的普遍性。代理还持续惩罚赞助标签，奖励平台推荐，且对价格、评分与评论的敏感度在不同模型间差异巨大。最后，我们证明卖家可应对：一个简单的卖方代理通过条件化描述调整，即可显著提升市场占有率。这些发现揭示了代理市场的高波动性和根本不同于人类主导的商业形态，凸显持续审计的必要性，并引发平台设计、卖家策略与监管层面的深层问题。
原文摘要 · Abstract (English)
Online marketplaces will be transformed by autonomous AI agents acting on behalf of consumers. Rather than humans browsing and clicking, AI agents can parse webpages or leverage APIs to view, evaluate and choose products. We investigate the behavior of AI agents using ACES, a provider-agnostic framework for auditing agent decision-making. We reveal that agents can exhibit choice homogeneity, often concentrating demand on a few ``modal'' products while ignoring others entirely. Yet, these preferences are unstable: model updates can drastically reshuffle market shares. Furthermore, randomized trials show that while agents have improved over time on simple tasks with a clearly identified best choice, they exhibit strong position biases -- varying across providers and model versions, and persisting even in text-only "headless" interfaces -- undermining any universal notion of a ``top'' rank. Agents also consistently penalize sponsored tags while rewarding platform endorsements, and sensitivities to price, ratings, and reviews vary sharply across models. Finally, we demonstrate that sellers can respond: a seller-side agent making simple, query-conditional description tweaks can drive significant gains in market share. These findings reveal that agentic markets are volatile and fundamentally different from human-centric commerce, highlighting the need for continuous auditing and raising questions for platform design, seller strategy and regulation.
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。