Multi-agent ai system improves seller visibility in online shopping
Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce
Artificial IntelligenceInformation Retrieval
Summary
Online shopping assistants now guide what shoppers find, making it hard for sellers to compete. The authors created a system with multiple AI agents that measures how visible a seller is when shoppers search and figures out why visibility changes. By testing parts of the system, they found it can recover important signals much better than guessing. This helps sellers decide how to improve their product placement in online shops.
What this means in practice
- •For e-commerce marketing teams: Identify and prioritize merchandising changes to improve product visibility on AI-driven shopping platforms.
- •For digital retail platform operators: Automate competitive visibility tracking across multiple AI search platforms to optimize seller outcomes.
Authors
Spandan Ghose Chowdhury
Abstract
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.