MALTopic: Multi-Agent LLM Topic Modeling Framework
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured or categorical survey responses for topic modeling. And they produce abstract topics, requiring extensive human interpretation. To address these limitations, we propose the Multi-Agent LLM Topic Modeling Framework (MALTopic). This framework decomposes topic modeling into specialized tasks executed by individual LLM agents: an enrichment agent leverages structured data to enhance textual responses, a topic modeling agent extracts latent themes, and a deduplication agent refines the results. Comparative analysis on a survey dataset demonstrates that MALTopic significantly improves topic coherence, diversity, and interpretability compared to LDA and BERTopic. By integrating structured data and employing a multi-agent approach, MALTopic generates human-readable topics with enhanced contextual relevance, offering a more effective solution for analyzing complex survey data.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 7 of its 17 references that are in the map. First posted on arXiv 7 Jan 2026.
Builds on
7 of 17 references.
References · 7
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
- 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
- 2024Large Language Models Offer an Alternative to the Traditional Approach of Topic Modellingcited by 35
- 2024LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Modelscited by 11
- 2024Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEscited by 5
- 2024Qualitative Insights Tool (QualIT): LLM Enhanced Topic Modelingcited by 4
- 2024Capturing research literature attitude towards Sustainable Development Goals: an LLM-based topic modeling approachcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration
- 2025Agentic AutoSurvey: Let LLMs Survey LLMs
- 2026SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation
- 2026Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiency
- 2026Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
- 2025SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation
- 2025Creating Targeted, Interpretable Topic Models with LLM-Generated Text Augmentation
- 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research