Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce
Summary
This paper introduces a multi-agent AI system for measuring and diagnosing competitive visibility in LLM-mediated e-commerce using Agentic Share-of-Search, with an ablation study showing feasibility.
View Cached Full Text
Cached at: 09/12/26, 08:24 AM
# Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce Source: [https://arxiv.org/abs/2609.11190](https://arxiv.org/abs/2609.11190) [View PDF](https://arxiv.org/pdf/2609.11190) > 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\. ## Submission history From: Spandan Ghose Chowdhury \[[view email](https://arxiv.org/show-email/793d6ed1/2609.11190)\] **\[v1\]**Thu, 10 Sep 2026 07:55:59 UTC \(130 KB\)
Similar Articles
Iterating Toward Better Search: A Two-Agent Simulation Framework for Evaluating Agentic Search Architectures in E-Commerce
This paper from eBay presents a modular two-agent simulation framework for evaluating conversational shopping assistant architectures, enabling controlled comparisons of responder designs. Key findings include that rolling-window memory outperforms intent-extraction memory by 35% in speed, and that systematic failure analysis reduced failure rates by 62%.
Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
Introduces Agent Bazaar, a multi-agent simulation framework for evaluating economic alignment of LLMs, identifying failure modes like algorithmic instability and Sybil deception, and training a 9B model that outperforms frontier models using targeted reinforcement learning.
E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation
E-Commerce Bench is an open-source benchmark that evaluates LLM agents on long-horizon autonomous business operation in e-commerce, featuring multi-store negotiation and dynamic events over a simulated year.
EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
Introduces EComAgentBench, a benchmark for evaluating LLM-based shopping agents on long-horizon tasks with hidden intents distributed across queries, profiles, and clarifications. The benchmark uses real Amazon products and automated scoring, revealing that even the best model achieves only 57.1% accuracy.
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
The paper introduces Sealed Joint Search (SJS) and the Agora system, where five specialized LLM agent classes collaborate to evolve alpha factors. On a 91-day CSI 1000 holdout, Agora achieves a portfolio Sharpe of +1.87, significantly outperforming baselines, and the discovered metrics appear as emergent properties of the system.