Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews
For businesses and decision-support systems, this work provides a structured, cost-aware method to generate high-quality advice from review data, though it is an incremental improvement over existing LLM-based approaches.
The paper tackles converting customer reviews into actionable business advice. The proposed multi-agent pipeline improves advice quality over single-pass LLM baselines, with human evaluators preferring its recommendations.
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.