2026/07/20 by Abdelhak Kelious, Chyrine Tahri, Eliot Bardet
Computer Science · #Code (set theory) #Documentation #Graph #Model-Driven Software Engineering Techniques #Semantics (computer science) #Software #Software Engineering Research #Software system #Source code #Topic Modeling #Tree traversal #cs.AI #cs.SE
paper · pdf · doi:10.1145/3820755.3832807
openalex publication_date 2026/07/20 · openalex created_date 2026/07/24 · openalex updated_date 2026/08/01
Maintaining up-to-date code documentation is difficult in fast-moving repositories because design knowledge is scattered across source files and pull requests. We present CODENS , a system that turns pull requests into living, accessible, and queryable documentation for production codebases. CODENS incrementally builds a typed software knowledge graph from pull requests, enriches components through schema-driven semantic extraction, derives typed relations between them, and exposes the resulting knowledge through three retrieval modes, including agent-guided graph traversal for repository-level question answering. The system also preserves semantic change history across pull requests and integrates both answer-quality and operational evaluation metrics. We evaluate CODENS on a client Ruby on Rails project in production. Results show that CODENS produces highly relevant and well-grounded answers, while qualitative feedback highlights a remaining challenge in concise, documentation-oriented synthesis.