Metraipolis › archive › dc_33cf644c8a2f

Graph-Guided Repository Environment Construction — arXiv:2609.33429

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33429
License (as archived): CC0-1.0
Archived: 2026-10-07T21:01:27.848Z
SHA-256 of the archived text: f7b074106d1499176613819bab2eaea0b4b3bb4ed986f9ec0218a28190394fc1
Stable URL of this page: https://metraipolis.com/documento/dc_33cf644c8a2f

How to cite

Graph-Guided Repository Environment Construction — arXiv:2609.33429 — arXiv (en), https://arxiv.org/abs/2609.33429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33cf644c8a2f (Metraipolis archive dc_33cf644c8a2f, sha256 f7b074106d1499176613819bab2eaea0b4b3bb4ed986f9ec0218a28190394fc1)

BibTeX

@misc{dc33cf644c8a2f,
  title = {Graph-Guided Repository Environment Construction — arXiv:2609.33429},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33429},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33cf644c8a2f; sha256 f7b074106d1499176613819bab2eaea0b4b3bb4ed986f9ec0218a28190394fc1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents now increasingly rely on execution to validate their solutions, making the construction of reliable execution environments a critical enabling capability. However, repository environment construction is challenging because execution requirements are fragmented across repository artifacts and may only become apparent during execution. Existing agent-based approaches address this problem through iterative interaction, but information about the current construction state, including discovered requirements, satisfied and unresolved prerequisites, and their dependencies, can remain distributed across the interaction history. We present Graph2Env, an agent-based approach centered on DepGraph, a typed dependency graph that explicitly represents the environment requirements needed for repository execution, their dependency relations, and their states. Graph2Env uses DepGraph to guide environment construction and continuously refines it with execution feedback, while persisting successful repairs into a replayable construction procedure. The resulting artifacts are then applied in a fresh environment to verify that the constructed environment can be reproduced. We evaluate Graph2Env on a benchmark of 200 Python repositories drawn from RATBench and EnvBench, against a static dependency-inference baseline (pipreqs), three specialized environment-construction systems (Repo2Run, RAT, and SetupX), and two general-purpose coding agents (SWE-agent and Claude Code). Graph2Env achieves an 81.0% Environment Build Success Rate (EBSR) and a 59.3% Environment Setup Success Rate (ESSR), outperforming the strongest baseline by 9.5 and 9.0 percentage points, respectively.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33429 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:02.662Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).