RetailBridge 基准与 RetailRAG 框架：面向企业零售异构数据源的 Agentic RAG 研究

View PDF HTML (experimental)

Abstract:Enterprise retail workflows require agents to chain evidence across heterogeneous sources, from structured product and order records to unstructured inquiries and reviews, yet existing agentic RAG benchmarks rarely capture this challenge. To enable controlled evaluation of such workflows, we introduce RetailBridge, a compositional retail benchmark built from persona-driven simulations. Its questions are constructed by linking entities and intermediate answers across heterogeneous sources, requiring agents to identify the relevant sources, carry evidence between them, and produce a grounded answer. To systematically evaluate LLMs on these retail workflows, we develop RetailRAG, a retail-aware framework equipped with auto-schema briefing, source-routed plan chaining, and diagnostic plan revision. RetailRAG consistently outperforms existing agentic RAG baselines across all evaluation axes, serving as a strong reference system for assessing LLM agents on retail workflows. On RetailBridge, evaluating ten LLM backbones with RetailRAG reveals multi-source chaining as the dominant bottleneck across providers and model scales, suggesting that reliable retail agents require explicit cross-source orchestration rather than scaling alone. Code and data are publicly available at this https URL.

Comments:	Accepted to KDD 2027 Datasets and Benchmarks Track (Cycle 1)
Subjects:	Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
Cite as:	arXiv:2610.25096 [cs.AI]
	(or arXiv:2610.25096v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.25096 arXiv-issued DOI via DataCite

Submission history

From: Jeonghwan Choi [view email]
[v1] Sun, 18 Oct 2026 08:15:12 UTC (1,361 KB)
[v2] Wed, 11 Nov 2026 13:16:49 UTC (1,359 KB)