paper-with-me

Papers

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

2025-04-11 · Dayu Yang, Antoine Simoulin, Xin Qian, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Grey Yang

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.

📄 PDF Abstract BibTeX arXiv:2504.08725

Code (1)

facebookresearch/docagent 공식 구현

Tasks

Code Documentation Generation

Similar Papers 제목 키워드 기반

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

2025-03-18 · Siwei Han, Peng Xia, Ruiyi Zhang, Tong Sun 외

Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information…

document understandingQuestion AnsweringRAGRetrieval+1

Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation

2026-05-14 · Suyoung Bae, Jaehoon Lee, Changkyu Choi, YunSeok Choi 외 arxiv

Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level ap…

Hybrid Retriever Evolution for Multimodal Document Reasoning Agents

2026-06-28 · Bohan Yao, Shruthan Radhakrishna, Vikas Yadav arxiv

Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that canno…

Question Answering

Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports

2026-04-04 · Yi-Cheng Wang, Wei-An Wang, Chu-Song Chen arxiv

Despite the strong language understanding abilities of large language models (LLMs), they still struggle with reliable question answering (QA) over long, structured documents, particularly for numerical reasoning. Financ…

Question Answering

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

2025-04-30 · Shaokun Zhang, Ming Yin, Jieyu Zhang, Jiale Liu 외

Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we pr…