mlsanityData to 7 Oct 2026

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

arXiv 2601.12024 ↗First posted 17 Jan 2026cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 19 of its 36 references that are in the map. First posted on arXiv 17 Jan 2026.

Builds on

19 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendation23 Feb
  2. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems13 Oct

Other references · 17

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  8. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  9. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  10. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
  11. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  12. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 171
5 more
  1. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  2. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  3. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMscited by 33
  4. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Taskscited by 30
  5. 2025MALLM: Multi-Agent Large Language Models Frameworkcited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025No-Human in the Loop: Agentic Evaluation at Scale for Recommendation
  2. 2026Align Generative Artificial Intelligence with Human Preferences: A Novel Large Language Model Fine-Tuning Method for Online Review Management
  3. 2026RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
  4. 2026Understanding Dominant Themes in Reviewing Agentic AI-authored Code
  5. 2024Designing Heterogeneous LLM Agents for Financial Sentiment Analysis
  6. 2026TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis
  7. 2025Are You Sure You're Positive? Consolidating Chain-of-Thought Agents with Uncertainty Quantification for Aspect-Category Sentiment Analysis
  8. 2026Sequence-aware Large Language Models for Explainable Recommendation ↗