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!
_version_ 1866917455967813632
author Bhandari, Kartikey Singh
Jain, Tanish
Agrawal, Archit
Kumar, Dhruv
Kumar, Praveen
Narang, Pratik
author_facet Bhandari, Kartikey Singh
Jain, Tanish
Agrawal, Archit
Kumar, Dhruv
Kumar, Praveen
Narang, Pratik
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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews
Bhandari, Kartikey Singh
Jain, Tanish
Agrawal, Archit
Kumar, Dhruv
Kumar, Praveen
Narang, Pratik
Artificial Intelligence
Computation and Language
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.
title Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2601.12024