Abstract:Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process components independently, causing redundant retrieval and conflicting descriptions across documents while producing outputs that lack hierarchical structure. Therefore, we propose MemDocAgent, a long-horizon agentic framework that generates documentation within a single, integrated context spanning the entire repository. It combines two components: (i) Dependency-Aware Traversal Guiding that predetermines a traversal order respecting dependency and granularity hierarchies; (ii) Memory-Guided Agentic Interaction, in which the agent interacts with RepoMemory, a shared memory accumulating prior work traces through read, write, and verify operations. Through an in-depth multi-criteria evaluation, MemDocAgent achieves the best performance over both open and closed-source baselines and demonstrates practical applicability in real software development workflows.
| Subjects: | Software Engineering (cs.SE); Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.14563 [cs.SE] |
| (or arXiv:2605.14563v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14563 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Suyoung Bae [view email]
[v1]
Thu, 14 May 2026 08:35:20 UTC (1,254 KB)