DocAgent: A Multi-Agent System for Automated Code Documentation Generation
This addresses the challenge of reliable code documentation generation for software developers, especially in complex repositories, though it appears incremental as it builds on existing multi-agent and LLM approaches.
The paper tackles the problem of generating high-quality code documentation automatically using Large Language Models, which often produce incomplete or incorrect outputs, and introduces DocAgent, a multi-agent system that significantly outperforms baselines in experiments.
High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete, unhelpful, or factually incorrect outputs. We introduce DocAgent, a novel multi-agent collaborative system using topological code processing for incremental context building. Specialized agents (Reader, Searcher, Writer, Verifier, Orchestrator) then collaboratively generate documentation. We also propose a multi-faceted evaluation framework assessing Completeness, Helpfulness, and Truthfulness. Comprehensive experiments show DocAgent significantly outperforms baselines consistently. Our ablation study confirms the vital role of the topological processing order. DocAgent offers a robust approach for reliable code documentation generation in complex and proprietary repositories.