Metraipolis › archive › dc_9ab87cdcce81

EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup — arXiv:2609.07357

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07357
License (as archived)
CC0-1.0
Archived
2026-10-16T14:09:05.477Z
SHA-256 of the archived text
ddf05eb2e0679f8d744eb7bf8a3880919537a7579ef6e6f923e09d066771c4bb
Stable URL of this page
https://metraipolis.com/documento/dc_9ab87cdcce81

How to cite

EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup — arXiv:2609.07357 — arXiv (en), https://arxiv.org/abs/2609.07357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ab87cdcce81 (Metraipolis archive dc_9ab87cdcce81, sha256 ddf05eb2e0679f8d744eb7bf8a3880919537a7579ef6e6f923e09d066771c4bb)
BibTeX
@misc{dc9ab87cdcce81,
  title = {EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup — arXiv:2609.07357},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07357},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ab87cdcce81; sha256 ddf05eb2e0679f8d744eb7bf8a3880919537a7579ef6e6f923e09d066771c4bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Environment Setup is a critical yet complex task in software engineering that relies heavily on expert knowledge. Existing automated environment setup methods lack the ability to accumulate experience from past execution trajectories and to evolve over time. As a result, their performance is limited because they often perform redundant exploration, ignore useful past solutions, and fail to generalize across diverse software ecosystems. We present the systematic design and empirical validation of EnvPilot, an experience-augmented agent that operationalizes trajectory-derived experience reuse for software environment setup. EnvPilot maintains an expandable Trajectory-Derived Memory (TDM), initialized with 667 high-quality experiences. It systematically transforms implicit knowledge from historical execution trajectories into structured experience and retrieves the most relevant guidance during task execution through the Context-aware Retrieval mechanism. This enables EnvPilot to combine multiple validated setup strategies, providing more precise and detailed guidance than methods that rely solely on static project files or web retrieval. To evaluate EnvPilot, we construct AES-Bench, a multilingual benchmark of 112 real-world GitHub instances across 9 programming languages. Experiments show that EnvPilot achieves a new state-of-the-art (SOTA) with a 75.00% Pass@1 success rate while reducing reasoning costs. Our empirical study shows that both the structured experience representation and the Context-aware Retrieval mechanism are essential.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.07357 — 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 2026-10-16T13:58:36.382Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).