发表机构
Tsinghua University; Tencent Inc.（清华大学; 腾讯公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于LLM的代理推荐市场，用户先提需求平台竞争注意力。实验发现新设置在获取与注意力间有紧张关系，竞争引发平台策略行为，关联反馈可增加购买机会，强调设计代理推荐需综合考虑多方面并作为联合机制设计问题。
AI 中文摘要
传统在线推荐在用户进入平台后进行，由平台决定候选池和展示给用户的排名。基于大语言模型（LLM）的用户代理实现了不同的推荐过程：用户在选择平台前指定需求，让平台竞争用户注意力，即代理推荐市场。在基于LLM的三个产品领域的控制实验中，发现这种新推荐设置在获取与注意力间产生了紧张关系。与传统以平台为中心的推荐相比，以用户为中心的推荐极大地扩大了相关项目进入比较的机会，但更广泛参与并未直接转化为有效曝光。竞争直接引发平台的策略行为，当用户代理将平台行动与后续用户反馈关联时，购买相关项目的机会增加。因此，设计代理推荐需要将获取、注意力和问责视为联合机制设计问题。
英文摘要
Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the user. LLM-based user agents enable a different recommendation process: a user specifies a need before choosing a platform, leaving platforms to compete for the user's attention, which we refer to as an agentic recommendation market. In our controlled LLM-based experiments across three product domains, we find this new setting of recommendation creates a tension between access and attention. Compared with traditional platform-centric recommendation, user-centric recommendation greatly expands the opportunity for relevant items to enter comparison; yet broader participation does not translate directly into effective exposure. Competition directly triggers platforms' strategic play: selectively positive explanations occupy 73--78% of first-ranked positions. When the user agent relates platforms' actions to subsequent user feedback, this share falls to 36--41%, while the chance of a user purchasing the relevant item increases. A user agent is therefore more than a ranker over a larger pool of candidates: its querying, ranking, and feedback mechanism governing who can compete, how scarce attention is allocated, and how earlier outcomes shape the evaluation of platforms directly affect user utility. Designing agentic recommendation therefore requires treating access, attention, and accountability as a joint mechanism design problem.
