AI代理购物时，排名影响变弱，页面内容更重要。
Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
- 随机打乱100个酒店列表顺序，测试AI代理搜索行为。
- 中间位置最不被查看，排名不再单调影响选择结果。
- 不同模型对排名敏感度不同，但最终都选相同最优项。
搜索排名之所以重要，是因为人类注意力稀缺且具有顺序性。排位靠前的选项更易被发现，因而被查看和购买的概率更高。如今消费者正将搜索任务委托给能一次性读取整页结果的AI代理。在5000次AI代理会话中，对100个酒店列表进行排序随机化，比较四种大语言模型与人类实地数据的表现。结果显示，AI代理比人类搜索更深，且从不拒绝购买。虽然位置仍能预测哪些列表被查看，但影响较弱且非单调：页面中部被查看概率最低，而非底部。位置影响仅部分模型达到决策阶段，且这种差异与模型提供方或能力无关。然而，所有模型最终都收敛至同一非劣解列表。对于代理式搜索，页面展示的属性比位置更重要。
原文摘要 · Abstract (English)
Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives are easier to find, so they are examined and bought more often. Consumers are now delegating search to AI agents that can ingest an entire results page at once. Randomizing the order of one hundred hotel listings across 5,000 AI agent sessions, we compare four large language models against human field data. AI agents search more deeply than humans and never decline to buy. Position still predicts which listings are inspected, but weakly and non-monotonically: the middle of a results page has the lowest probability of inspection, not the bottom. Position reaches the choice stage for some models and not others, a heterogeneity that tracks neither provider nor capability. All models nonetheless converge on the same undominated listing. For agentic search, the attributes displayed on a results page matter more than placement within it.
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。