Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach

2026-06-23

AI Summary

This work addresses the challenge of generating concise and accurate summaries from lengthy and complex software documentation, a task for which manual approaches are inefficient and impractical. To this end, the authors propose Metagente, a novel system that introduces a multi-agent collaborative framework into the document summarization process. Metagente employs a teacher–student architecture grounded in large language models (LLMs), where specialized agents collaborate through role-based division of labor and knowledge distillation. Experimental results on real-world datasets demonstrate that Metagente significantly outperforms existing baseline methods, yielding summaries with higher relevance and accuracy. Furthermore, the system effectively supports downstream tasks such as requirements analysis and technical documentation processing, thereby advancing the deep integration of LLMs into software engineering practices.

Abstract

Large Language Models (LLMs) and LLM-based Multi-Agent Systems (MAS) are revolutionizing software engineering (SE) by advancing automation, decision-making, and knowledge processing. Their recent application to SE tasks has already shown promising results. In this paper, we focus on summarization as a key application area. We present Metagente, an LLM-based MAS designed to generate concise and accurate summaries of software documentation. Metagente employs a Teacher-Student architecture where multiple LLM agents collaborate to enhance relevance and precision of produced summaries. An empirical evaluation on real-world datasets demonstrates Metagente's effectiveness in streamlining workflows, outperforming the considered baselines. The evaluation provides evidence that Metagente improves summarization for requirements analysis and technical documentation. Our findings underscore the transformative potential of these technologies in SE, while identifying challenges and future research directions for their seamless integration.

Problem

• Automated Summarization
• Software Documents
• LLM-based Multi-Agent Systems
• Requirements Analysis
• Technical Documentation

Innovation

• LLM-based Multi-Agent System
• Software Document Summarization
• Teacher-Student Architecture
• Automated Summarization
• Software Engineering