Saved in:
Bibliographic Details
Main Authors: Bhandari, Kartikey Singh, Jain, Tanish, Agrawal, Archit, Kumar, Dhruv, Kumar, Praveen, Narang, Pratik
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.12024
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.