Newest papers

Code Comprehensor: Hierarchical Documentation and Cross-Modal Retrieval for Large Repositories

Sujoy Roychowdhury, Joseph H. R. Isaac, Jiangning Gao, Martin Klitte, Diarmuid Corcoran · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30016 · open-access PDF

Korean

대규모, 복잡하고 빠르게 진화하는 코드베이스를 이해하는 것은 소프트웨어 엔지니어링의 핵심 과제로 남아 있으며, 삽입, 유지 보수, 재현 및 영향 분석을 방해합니다. Large-Language Model (LLM)에이 정보를 제공하는 것은 LLM이 필요한 코드 방법뿐만 아니라 저장소의 대형 계획에 관련된 방법을 이해해야하기 때문에 또 다른 장애물입니다. 우리는 (i) 코드 의존 Callgraph, (ii) CodeScribe를 결합하는 하이레라크 문서 인증을 생성하기 위해 코드 인식 LLM을 사용하는 하이레라크 문서 인식 프레임 워크 코드 Comprehensor를 제안합니다.

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

Abstract

Understanding large, complex, and rapidly evolving code bases remains a core challenge for software engineering at scale, hindering onboarding, maintenance, refactoring, and impact analysis. Providing this information to a Large-Language Model (LLM) is another hurdle, as the LLM must understand not only the required code method but also its associated methods in the grand scheme of the repository. We propose Code Comprehensor, a hybrid retrieval-reasoning framework combining (i) a code dependency callgraph, (ii) CodeScribe, which uses code-aware LLMs to generate hierarchical documentation acro

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30016, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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