用用户点击反馈自动优化搜索标题，提升点击率
MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
- 多智能体框架从点击数据中学习优质标题模式
- 实测点击率提升10.26%，点击量增7.51%
- 适合无法获取标注数据的黑箱系统内容优化
元标题和描述对搜索与推荐平台的用户参与度有重要影响，但优化仍具挑战。搜索引擎排名模型为黑箱环境，缺乏显式标签，点击率（CTR）等反馈仅在部署后出现。现有模板、大模型及检索增强方法或缺乏多样性，或产生幻觉，或忽略候选表述的历史排名表现。为此，我们提出MetaSynth，一种基于隐式搜索反馈的多智能体检索增强生成框架。该框架从高排名结果构建范例库，结合产品内容与范例生成候选摘要，并通过评估-生成循环迭代优化，确保相关性、促销力度与合规性。在自有电商数据集与Amazon Reviews语料上，MetaSynth在NDCG、MRR及排序指标上均优于强基线。大规模A/B测试进一步验证了10.26%的CTR提升与7.51%的点击增长。本工作不仅优化元数据，更提出一种利用隐式信号在黑箱系统中优化内容的通用范式。
原文摘要 · Abstract (English)
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box environments, explicit labels are unavailable, and feedback such as click-through rate (CTR) arrives only post-deployment. Existing template, LLM, and retrieval-augmented approaches either lack diversity, hallucinate attributes, or ignore whether candidate phrasing has historically succeeded in ranking. This leaves a gap in directly leveraging implicit signals from observable outcomes. We introduce MetaSynth, a multi-agent retrieval-augmented generation framework that learns from implicit search feedback. MetaSynth builds an exemplar library from top-ranked results, generates candidate snippets conditioned on both product content and exemplars, and iteratively refines outputs via evaluator-generator loops that enforce relevance, promotional strength, and compliance. On both proprietary e-commerce data and the Amazon Reviews corpus, MetaSynth outperforms strong baselines across NDCG, MRR, and rank metrics. Large-scale A/B tests further demonstrate 10.26% CTR and 7.51% clicks. Beyond metadata, this work contributes a general paradigm for optimizing content in black-box systems using implicit signals.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。