智能体搜索份额：用于LLM中介电子商务竞争决策的多智能体AI系统
Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce
- College of Computing, Georgia Institute of Technology（佐治亚理工学院计算学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一个多智能体AI系统，以智能体搜索份额为决策目标，自动测量和诊断LLM中介电商中的竞争可见性问题，并通过消融实验验证其有效性。
AI中文摘要：
AI购物助手日益引导消费者发现商品，这催生了对支持卖方竞争决策工具的迫切需求。我们提出一个多智能体AI系统，用于在LLM中介的电子商务中自动化竞争可见性测量和根因诊断。该系统引入智能体搜索份额（ASoS）作为决策目标，在领先的AI平台上部署查询智能体，并使用基于ReAct的诊断智能体推荐优先的营销干预措施。一项包含100次试验的消融研究，作为该原型的可行性评估，显示该智能体在39%的试验中恢复了被消融的信号（95%置信区间：30.0%-48.8%，是随机水平的5.5倍），在高相关性消融中恢复率升至63.9%。
英文摘要：
AI shopping assistants increasingly redirect consumer discovery, creating an urgent need for tools that support seller-side competitive decision-making. We present a multi-agent AI system that automates competitive visibility measurement and root cause diagnosis in LLM-mediated ecommerce. The system introduces Agentic Share-of-Search (ASoS) as the decision target, deploys query agents across leading AI platforms, and uses a ReAct-based diagnostic agent to recommend prioritized merchandising interventions. A 100-trial ablation study, presented as a feasibility evaluation of this prototype, shows the agent recovers the ablated signal in 39% of trials (95% CI: 30.0% - 48.8%, 5.5x over chance), rising to 63.9% among high-correlation ablations.
