Beyond Retrieval-Ranking: A Multi-Agent Cognitive Decision Framework for E-Commerce Search
Zhouwei Zhai, Mengxiang Chen, Haoyun Xia, Jin Li, Renquan Zhou, Min Yang
TL;DR
The paper tackles the misalignment of traditional retrieval-ranking with users' multi-stage cognitive shopping processes, which leads to semantic gaps, high decision costs, and lack of expert guidance. It introduces MACDF, a multi-agent cognitive decision framework with specialized agents (Leader, Guider, Planner, ProductSearch, WebSearch, Decider) and a Memory System to proactively support shopping decisions and minimize decision cost. Offline ECCD-Bench experiments and online JD A/B tests show MACDF outperforms retrieval-based baselines in accuracy, user satisfaction, conversion rate, and reduces reformulation burden, at the cost of higher latency that is partially mitigated by optimizations. The work demonstrates a paradigm shift from passive retrieval to active decision guidance, with practical impact on user experience and platform metrics, and outlines future avenues for efficiency, long-term value evaluation, and ablation studies.
Abstract
The retrieval-ranking paradigm has long dominated e-commerce search, but its reliance on query-item matching fundamentally misaligns with multi-stage cognitive decision processes of platform users. This misalignment introduces critical limitations: semantic gaps in complex queries, high decision costs due to cross-platform information foraging, and the absence of professional shopping guidance. To address these issues, we propose a Multi-Agent Cognitive Decision Framework (MACDF), which shifts the paradigm from passive retrieval to proactive decision support. Extensive offline evaluations demonstrate MACDF's significant improvements in recommendation accuracy and user satisfaction, particularly for complex queries involving negation, multi-constraint, or reasoning demands. Online A/B testing on JD search platform confirms its practical efficacy. This work highlights the transformative potential of multi-agent cognitive systems in redefining e-commerce search.