用多智能体模拟优化电商搜索词重写，提升用户意图匹配度。
OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation
- 构建多个模拟买家的LLM智能体，动态评估重写效果。
- 在1000条真实查询上平均提升21.98%，优于基线3.36%。
- 适合需要高精度搜索优化的电商平台和算法团队。
部署高效且符合用户需求的基于大语言模型的系统需要可靠的评估方法。尽管大语言模型在可验证任务（如编程、数学）中表现优异，但对缺乏唯一正确答案的主观任务仍面临挑战。电商搜索词重写（QR）即属此类问题：难以通过算法判断重写后的查询是否准确捕捉用户意图。本文提出OptAgent框架，结合多智能体模拟与遗传算法，实现对查询重写的验证与优化。不同于依赖静态奖励模型或单一LLM评判的方法，本方案让多个基于LLM的智能体分别扮演模拟购物者，以它们评分的平均值作为进化算法的适应度函数，迭代优化初始查询。我们在涵盖五个类别的1000条真实电商查询上进行评估，结果显示，相比原始查询平均提升21.98%，比Best-of-N LLM重写基线提升3.36%。
原文摘要 · Abstract (English)
Deploying capable and user-aligned LLM-based systems necessitates reliable evaluation. While LLMs excel in verifiable tasks like coding and mathematics, where gold-standard solutions are available, adoption remains challenging for subjective tasks that lack a single correct answer. E-commerce Query Rewriting (QR) is one such problem where determining whether a rewritten query properly captures the user intent is extremely difficult to figure out algorithmically. In this work, we introduce OptAgent, a novel framework that combines multi-agent simulations with genetic algorithms to verify and optimize queries for QR. Instead of relying on a static reward model or a single LLM judge, our approach uses multiple LLM-based agents, each acting as a simulated shopping customer, as a dynamic reward signal. The average of these agent-derived scores serves as an effective fitness function for an evolutionary algorithm that iteratively refines the user's initial query. We evaluate OptAgent on a dataset of 1000 real-world e-commerce queries in five different categories, and we observe an average improvement of 21.98% over the original user query and 3.36% over a Best-of-N LLM rewriting baseline.
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。