mlsanityData to 14 Oct 2026

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

arXiv 2504.08725 ↗First posted 11 Apr 2025cs.SE cs.AI cs.CLcited by 18

On the map: LLM agents and tool use → Software engineering coding agents

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.

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.

Builds on

21 of 47 references.

References · 21

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  6. 2023Teaching Large Language Models to Self-Debugcited by 988
  7. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  8. 2023StarCoder: may the source be with you!cited by 799
  9. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  10. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  11. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 575
  12. 2021Unified Pre-training for Program Understanding and Generationcited by 366
9 more
  1. 2022Efficient Training of Language Models to Fill in the Middlecited by 255
  2. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  3. 2024CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklistscited by 94
  4. 2020PyMT5: multi-mode translation of natural language and Python code with transformerscited by 80
  5. 2022When Language Model Meets Private Librarycited by 54
  6. 2025No Free Labels: Limitations of LLM-as-a-Judge Without Human Groundingcited by 54
  7. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  8. 2023A Comparative Analysis of Large Language Models for Code Documentation Generationcited by 24
  9. 2021Automatic API Usage Scenario Documentation from Technical Q&A Sitescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 11.

18 papers.

Sort:

By area:

  1. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
  2. 2025CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generationcited by 6
  3. 2026RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repaircited by 6
  4. 2026Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQAcited by 4
  5. 2025MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLMcited by 3
  6. 2026Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimizationcited by 3
  7. 2025VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systemscited by 1
  8. 2025From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detectioncited by 1
  9. 2026Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packagescited by 1
  10. 2026Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentationcited by 1
  11. 2025Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineeringcited by 0
  12. 2025A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Buildingcited by 0
6 more
  1. 2026AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interactioncited by 0
  2. 2026COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contextscited by 0
  3. 2026The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systemscited by 0
  4. 2026Communicating Chess Strategies in Natural Languagecited by 0
  5. 2026DocAtlas: Long-Document Understanding as Mutable-State Interactioncited by 0
  6. 2026SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specificationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  2. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
  3. 2025AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation
  4. 2025Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
  5. 2026Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
  6. 2026CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
  7. 2024CodeAgent: Autonomous Communicative Agents for Code Review
  8. 2025NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents