Metraipolis › archive › dc_86f594cb81fa

OpenDraco: A Platform for Engineering and Experimenting with Configurable Multi-Agent Architectures for Software Engineering — arXiv:2610.32686

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32686
License (as archived)
CC0-1.0
Archived
2026-10-26T20:15:42.491Z
SHA-256 of the archived text
f0023baaf470a4cf10763c73d03f457bd6d39da54fa6d7ac8d9fd9912dd7ed1e
Stable URL of this page
https://metraipolis.com/documento/dc_86f594cb81fa

How to cite

OpenDraco: A Platform for Engineering and Experimenting with Configurable Multi-Agent Architectures for Software Engineering — arXiv:2610.32686 — arXiv (en), https://arxiv.org/abs/2610.32686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86f594cb81fa (Metraipolis archive dc_86f594cb81fa, sha256 f0023baaf470a4cf10763c73d03f457bd6d39da54fa6d7ac8d9fd9912dd7ed1e)
BibTeX
@misc{dc86f594cb81fa,
  title = {OpenDraco: A Platform for Engineering and Experimenting with Configurable Multi-Agent Architectures for Software Engineering — arXiv:2610.32686},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32686},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86f594cb81fa; sha256 f0023baaf470a4cf10763c73d03f457bd6d39da54fa6d7ac8d9fd9912dd7ed1e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Experimenting with LLM-based multi-agent systems (MAS) involves an iterative cycle of modeling configurations, executing and evaluating them, comparing results, and refining system designs. Existing approaches provide limited end-to-end support for this experimentation lifecycle. We present OpenDraco, an open-source platform that integrates these activities into a single workflow. OpenDraco represents agents, prompts, tools, models, parameters, and communication topology in exportable, versioned JSON specifications, translated into executable LangGraph workflows supporting different interaction structures. Users can modify and re-evaluate configurations using local or cloud-based LLMs. We instantiate OpenDraco for automated program repair (APR) and evaluate a sequential baseline and seven reconstructed configurations on synthetic and real-world SWE-bench Lite issues. The results reveal substantial cost differences among configurations with similar repair outcomes, while the baseline resolves 12 of 77 SWE-bench issues using open-source LLMs. Additional proof-of-concept tasks illustrate applicability beyond APR. OpenDraco supports iterative experimentation with heterogeneous MAS configurations, enabling researchers to examine their outcomes and costs within a common environment. Demonstration video: this https URL .

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.32686 — 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 2026-10-26T19:49:18.385Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).