Metraipolis › archive › dc_c09fb8310f41

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives — arXiv:2610.07832

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07832
License (as archived)
CC0-1.0
Archived
2026-10-07T11:17:21.956Z
SHA-256 of the archived text
74aa872852827a29d44cf2d65dcd01f3acc931a300cc788304d4f3f6ed630a6f
Stable URL of this page
https://metraipolis.com/documento/dc_c09fb8310f41

How to cite

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives — arXiv:2610.07832 — arXiv (en), https://arxiv.org/abs/2610.07832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c09fb8310f41 (Metraipolis archive dc_c09fb8310f41, sha256 74aa872852827a29d44cf2d65dcd01f3acc931a300cc788304d4f3f6ed630a6f)
BibTeX
@misc{dcc09fb8310f41,
  title = {Harness Engineering for Software Engineering via Modular Executable Dev-Primitives — arXiv:2610.07832},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07832},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c09fb8310f41; sha256 74aa872852827a29d44cf2d65dcd01f3acc931a300cc788304d4f3f6ed630a6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce \textbf{Dev-Primitives} (\emph{Development Primitives}), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose \textbf{HERMES}, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4\% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5\% of the homogeneous GPT-5.6 Sol configuration across all four benchmarks, while reducing inference cost by 26.2\% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.07832 — 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 2026-10-07T11:15:09.481Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).