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

Indonesian

Pendekatan yang ada pada dasarnya memperlakukan dokumentasi sebagai pembuatan teks yang tidak terbatas, tidak memiliki spesifikasi kualitas yang eksplisit, sangat bergantung pada prompts konteks panjang atas kode mentah, dan menawarkan dukungan terbatas untuk penilaian yang dapat diulangi. Kami berpendapat bahwa pembuatan dokumentasi tingkat kode harus menjadi tugas rekayasa perangkat lunak yang dipandu oleh standar, di mana dokumentasi dihasilkan dan dievaluasi terhadap persyaratan kualitas yang eksplisit dan dapat diulang yang berasal dari standar otoritatif. Kami mendefinisikan dokumentasi kode sebagai deskripsi bahasa alami dari fungsi dan kelas repository, yang diatur oleh jalur kode sumber. Kami menyajikan CODOCED pada tugas rekayasa perangkat lunak yang dipandu oleh agen, kerangka kerja yang mengidentifikasi ketergantungan antara entitas kode melalui analisis static call-gra

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