Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.05991 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914539192188928 |
|---|---|
| author | Commerce Search Relevance Team |
| author_facet | Commerce Search Relevance Team |
| contents | Relevance is a foundation of user experience in e-commerce search. We view relevance optimization as a closed-loop ecosystem involving multiple human roles: users who provide feedback, product managers who define standards, annotators who label data, algorithm engineers who optimize models, and evaluators who assess performance. Because improving relevance in practice means systematically resolving user-perceived bad cases, we ask a system-level question: can this ecosystem be reimagined by replacing its human roles with autonomous agents? To answer this question, we propose a case-driven multi-agent framework that automates the pipeline from bad-case identification to resolution. The framework instantiates an Annotator Agent for multi-turn annotation, an Optimizer Agent for autonomous bad-case analysis and resolution, and a User Agent that identifies bad cases through conversational interaction, together forming an autonomous and continually evolving system. To make the framework practical in production, we further adopt a harness-engineering paradigm and build a unified retrieval-and-ranking relevance model for efficient training, an instruction-following relevance model for real-time case resolution, Global Memory to reduce information asymmetry across agents, a Deep Search Agent to target underestimation failures, and an agent-based chatbot for human--agent collaboration. Extensive human evaluation shows that the framework performs relevance-related tasks effectively, improves annotation accuracy, and enables more timely and generalizable bad-case resolution, indicating a practical paradigm for industrial search relevance optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05991 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Case-Driven Multi-Agent Framework for E-Commerce Search Relevance Commerce Search Relevance Team Information Retrieval Relevance is a foundation of user experience in e-commerce search. We view relevance optimization as a closed-loop ecosystem involving multiple human roles: users who provide feedback, product managers who define standards, annotators who label data, algorithm engineers who optimize models, and evaluators who assess performance. Because improving relevance in practice means systematically resolving user-perceived bad cases, we ask a system-level question: can this ecosystem be reimagined by replacing its human roles with autonomous agents? To answer this question, we propose a case-driven multi-agent framework that automates the pipeline from bad-case identification to resolution. The framework instantiates an Annotator Agent for multi-turn annotation, an Optimizer Agent for autonomous bad-case analysis and resolution, and a User Agent that identifies bad cases through conversational interaction, together forming an autonomous and continually evolving system. To make the framework practical in production, we further adopt a harness-engineering paradigm and build a unified retrieval-and-ranking relevance model for efficient training, an instruction-following relevance model for real-time case resolution, Global Memory to reduce information asymmetry across agents, a Deep Search Agent to target underestimation failures, and an agent-based chatbot for human--agent collaboration. Extensive human evaluation shows that the framework performs relevance-related tasks effectively, improves annotation accuracy, and enables more timely and generalizable bad-case resolution, indicating a practical paradigm for industrial search relevance optimization. |
| title | A Case-Driven Multi-Agent Framework for E-Commerce Search Relevance |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2605.05991 |