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.

翻译：元标题和描述在搜索与推荐平台中显著影响用户参与度，但其优化仍具挑战性。搜索引擎排序模型属于黑盒环境，缺乏显式标签，且点击率（CTR）等反馈仅在部署后产生。现有基于模板、大语言模型（LLM）和检索增强的方法要么多样性不足，要么生成虚构属性，或忽略候选表述在历史排序中的成功记录。这导致直接利用可观测结果中的隐式信号存在空白。本文提出MetaSynth，一种基于隐式搜索反馈的多智能体检索增强生成框架。MetaSynth从排名靠前的结果构建范例库，结合产品内容与范例生成候选摘要，并通过评估器-生成器循环迭代优化输出，以确保相关性、推广强度与合规性。在专有电商数据和亚马逊评论语料上的实验表明，MetaSynth在NDCG、MRR和排序指标上均优于强基线方法。大规模A/B测试进一步显示其点击率提升10.26%，点击量增长7.51%。除元数据优化外，本研究为利用隐式信号优化黑盒系统内容提供了一种通用范式。