# DocAgent: A Multi-Agent System for Automated Code Documentation Generation

arXiv: https://arxiv.org/abs/2504.08725 · HTML: https://mlsanity.com/paper/2504.08725/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 21 of 21)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists](https://mlsanity.com/paper/2403.18771/) (2024)
- [PyMT5: multi-mode translation of natural language and Python code with transformers](https://mlsanity.com/paper/2010.03150/) (2020)
- [When Language Model Meets Private Library](https://mlsanity.com/paper/2210.17236/) (2022)
- [No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding](https://mlsanity.com/paper/2503.05061/) (2025)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [A Comparative Analysis of Large Language Models for Code Documentation Generation](https://mlsanity.com/paper/2312.10349/) (2023)
- [Automatic API Usage Scenario Documentation from Technical Q&A Sites](https://mlsanity.com/paper/2102.08502/) (2021)

## Built on by (most cited first, 18 of 18)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generation](https://mlsanity.com/paper/2507.08325/) (2025)
- [RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair](https://mlsanity.com/paper/2603.01048/) (2026)
- [Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA](https://mlsanity.com/paper/2604.13731/) (2026)
- [MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM](https://mlsanity.com/paper/2509.17489/) (2025)
- [Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization](https://mlsanity.com/paper/2603.12933/) (2026)
- [VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems](https://mlsanity.com/paper/2509.11942/) (2025)
- [From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection](https://mlsanity.com/paper/2511.08060/) (2025)
- [Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages](https://mlsanity.com/paper/2601.12148/) (2026)
- [Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation](https://mlsanity.com/paper/2605.14563/) (2026)
- [Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering](https://mlsanity.com/paper/2511.19427/) (2025)
- [A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building](https://mlsanity.com/paper/2512.01434/) (2025)
- [AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction](https://mlsanity.com/paper/2603.05551/) (2026)
- [COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts](https://mlsanity.com/paper/2604.27389/) (2026)
- [The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems](https://mlsanity.com/paper/2606.30524/) (2026)
- [Communicating Chess Strategies in Natural Language](https://mlsanity.com/paper/2607.11486/) (2026)
- [DocAtlas: Long-Document Understanding as Mutable-State Interaction](https://mlsanity.com/paper/2608.07527/) (2026)
- [SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications](https://mlsanity.com/paper/2610.15708/) (2026)

## Abstract (arXiv)

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.