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

Korean

소프트웨어 저장소에 대한 고품질 문서를 자동으로 토코드 기반으로 생성하는 것은 여전히 도전적입니다 : 기존 접근 방식은 대부분 문서를 제한되지 않은 텍스트 생성으로 취급하며, 상당히 권위있는 표준에서 유래된 명시적 인 품질 요구 사항에 대한 명시적 인 사양이 부족합니다. Python은 코드 문서를 재생 가능한 평가 기능 및 클래스의 자연 언어 설명으로 정의합니다. 우리는 코드 수준의 문서 생성은 오래된 소스 코드 경로에 의해 조직되어야한다고 주장합니다. CODOCED는 표준 지시된 소프트웨어 엔지니어링 작업이며, 문서가 명시적이고 재사용 가능한 품질 요구 사항을 통해 문서 사이의 의존성을 식별하고 평가합니다. 우리는 공식적인 의존

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