Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews

TL;DR

This paper introduces a hierarchical multi-agent pipeline that improves the extraction of actionable business advice from customer reviews, outperforming standard LLM approaches in relevance, actionability, and redundancy.

Contribution

It presents a novel agent-based architecture that decomposes review analysis into structured steps, enabling better control, auditability, and quality of business recommendations.

Findings

The pipeline achieves consistent improvements over baseline LLM methods.

Human evaluators prefer recommendations generated by the proposed system.

Structured agent decomposition enhances scalability and cost-efficiency.

Abstract

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.