用多智能体架构从用户评价中生成可操作的商业建议
Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews
- 分阶段设计多个智能体，分别处理信号压缩、问题抽象和建议评估
- 在三个服务领域数据上，建议的可操作性、相关性和非重复性均优于单轮大模型
- 适合需要低成本、可审计商业决策支持的企业场景
客户评论蕴含服务品质的重要线索，但将大规模评论数据转化为可执行的商业建议仍具挑战。传统情感/方面分析多为描述性，直接调用大语言模型（LLM）常产生泛化且重复的建议，缺乏对用户反馈的有效支撑。本文提出一种分层决策支持管道，将信号压缩、问题抽象、候选生成、基于目标的评估与成本感知路由等步骤拆解为不同智能体。该架构生成可追溯的中间结果，实现建议质量与令牌预算之间的可控权衡。在三个服务领域的Yelp评论数据上，系统在可操作性、相关性和非冗余性等多个维度均显著优于单次调用的LLM基线。人工评估也显示用户更偏好本系统的推荐结果。这些发现表明，结构化智能体分解对可扩展、成本敏感的商业决策支持具有重要价值。
原文摘要 · Abstract (English)
Customer reviews contain valuable signals about service quality, but converting large-scale review corpora into actionable business recommendations remains difficult. Standard sentiment/aspect analysis is largely descriptive, while direct prompting of large language models (LLMs) often yields generic and repetitive advice that is weakly grounded in user feedback. We propose a hierarchical decision-support pipeline that explicitly separates signal compression, problem abstraction, candidate generation, objective-based evaluation, and cost-aware routing into different agents. This architectural decomposition produces auditable intermediate artifacts and enables controllable trade-offs between advice quality and token budget. Experiments on Yelp reviews from three service domains show consistent improvements over single-pass LLM baselines across multiple advice quality dimensions, including actionability, relevance, and non-redundancy. A human evaluation further indicates that users generally prefer our system's recommendations. These results highlight the value of structured agentic decomposition for scalable, cost-aware business decision support.
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。