Metraipolis › archive › dc_6cbc6eb6793e

ASAD: Adaptive Software Agents for Debugging — arXiv:2610.00629

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00629
License (as archived)
CC0-1.0
Archived
2026-10-06T15:16:54.505Z
SHA-256 of the archived text
bbac904fd26433850fb28211ae453e32349b8845b0b2ee28be9f4e87362b2535
Stable URL of this page
https://metraipolis.com/documento/dc_6cbc6eb6793e

How to cite

ASAD: Adaptive Software Agents for Debugging — arXiv:2610.00629 — arXiv (en), https://arxiv.org/abs/2610.00629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6cbc6eb6793e (Metraipolis archive dc_6cbc6eb6793e, sha256 bbac904fd26433850fb28211ae453e32349b8845b0b2ee28be9f4e87362b2535)
BibTeX
@misc{dc6cbc6eb6793e,
  title = {ASAD: Adaptive Software Agents for Debugging — arXiv:2610.00629},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00629},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6cbc6eb6793e; sha256 bbac904fd26433850fb28211ae453e32349b8845b0b2ee28be9f4e87362b2535},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The integration of Large Language Models (LLMs) into multi-agent systems has shown great potential for automated debugging. Yet nearly all current frameworks rely on rigid, predefined architectures: the number of agents, their roles, and their interaction patterns are fixed before any analysis of the bug occurs. This one-size-fits-all approach is fundamentally mismatched to the heterogeneous nature of software defects. Simple bugs waste resources on unnecessary coordination, while complex ones suffer from insufficient or poorly aligned expertise. This paper introduces ASAD, an adaptive agentic system for debugging that configures its team according to the nature and complexity of each bug. ASAD initiates the debugging process by analyzing the faulty code and dynamically determines the number of agents to deploy, the specialized roles they should have, and the collaboration strategy they should follow. A central coordinator orchestrates this process through iterative planning, reflection, and execution; applying fast single-pass repairs for simple issues while assembling purpose-built teams to tackle more complex failures. We evaluate ASAD on three established benchmarks: Defects4J, DebugBench, and CodeFlaws, using multiple LLMs, such as DeepSeek-V3, Qwen-3 and GPT-5. ASAD consistently improves bug-fix rates by 12--20% over chain-of-thought(CoT) prompting and consistently outperforms static multi-agent systems by 4--9% in fix precision while reducing average agent usage by 32%. Crucially, our system dynamically adjusts the number and roles of agents: it resolves simple bugs with minimal coordination and scales agent involvement only for more complex cases.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-02 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.00629 — 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 2026-10-06T15:11:52.279Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).