Newest papers

Standards-Guided and Dependency-Aware Code-Level Documentation Generation

Tingxu Han, Wei Song, Ziming Li, Yuchen Chen, Weisong Sun, Zhenpeng Chen, Chunrong Fang, Zhenyu Chen, Yang Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27634 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

对于软件存储库来说,自动生成基于托克的高质量文档仍然是一个挑战:现有的方法主要是将文档视为无限制的文本生成,缺乏相对明确的质量规格,很大程度上依赖于长期背景的推文,并提供可重复的评估的有限支持。我们认为代码级的文档生成应该是标准引导的软件工程任务,其中文档是通过权威性标准产生的明确的、可重复使用的质量要求来生成和评估的。我们定义了代码文档是可重复的存储库功能和类的自然语言描述,由源代码路径组织。我们介绍了CODOCED,一个基于标准的研究和依赖意识的框架,该框架通过国家调用文本和ASTA的基本反馈分析来识别

Machine translation (Meta M2M100); the English original follows.

Abstract

Automatically generating high-quality documentation for software repositories remains challenging: existing approaches largely treat documentation as unconstrained text generation, lacking explicit quality specifications, depending heavily on long-context prompts over raw code, and offering limited support for reproducible evaluation. We argue that code-level documentation generation should instead be a standards-guided software engineering task, in which documentation is generated and assessed against explicit, reusable quality requirements derived from authoritative standards. We define code documentation as natural-language descriptions of repository functions and classes, organized by source-code path. We present CODEDOC, a standards-guided and dependency-aware framework that identifies dependencies between code entities via static call-graph and AST analysis and constructs dependency-aware structured prompts combining local code context, repository paths, and documentation criteria drawn from authoritative standards and style guides. We further introduce an interactive LLM-as-a-judge protocol that supplies criterion-aligned feedback to refine generated documentation along fine-grained dimensions from formal and practice-oriented standards. Experiments on ten open-source Python repositories show that CODEDOC produces higher-quality documentation than RepoAgent and a long-context baseline under standards-aligned evaluation, with relative improvements of 11.6%-17.0% and 21.4%-29.6%, respectively, while consuming roughly an order of magnitude fewer tokens per documentation entity than the long-context baseline. A human study confirms substantial alignment between LLM-based and human judgments (Spearman's rho = 0.72), and the relative findings hold across different judge LLMs. Code is available at https://github.com/ControllableModel/CodeDoc.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Documentation, Software documentation, Internal documentation, Computer science, Technical documentation, Software engineering

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange