Metraipolis › archive › dc_d499dbd3dcdb

Dittany: Contribution-Guided Repair Framework for MAS Applications — arXiv:2610.42144

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42144
License (as archived): CC0-1.0
Archived: 2026-11-02T04:54:24.903Z
SHA-256 of the archived text: 2d8e9cae7eb33ff970823ef11995c72ea3a99a184028a70151b195d1fab4aa10
Stable URL of this page: https://metraipolis.com/documento/dc_d499dbd3dcdb

How to cite

Dittany: Contribution-Guided Repair Framework for MAS Applications — arXiv:2610.42144 — arXiv (en), https://arxiv.org/abs/2610.42144 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d499dbd3dcdb (Metraipolis archive dc_d499dbd3dcdb, sha256 2d8e9cae7eb33ff970823ef11995c72ea3a99a184028a70151b195d1fab4aa10)

BibTeX

@misc{dcd499dbd3dcdb,
  title = {Dittany: Contribution-Guided Repair Framework for MAS Applications — arXiv:2610.42144},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42144},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d499dbd3dcdb; sha256 2d8e9cae7eb33ff970823ef11995c72ea3a99a184028a70151b195d1fab4aa10},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42144. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based multi-agent system (MAS) applications can produce useful intermediate results while leaving task requirements unsatisfied. Repairing such executions requires identifying the work still needed and the completed results that can support it. We present \tool, a contribution-guided runtime repair framework for MAS applications. \tool derives expected contributions and acceptance conditions from task requirements and method specifications, and connects their dependencies in a contribution graph. Runtime checks locate unmet conditions and establish which results remain usable. These results guide action-level correction when available inputs suffice, or graph-level recovery when prerequisites or unfinished work need revision. Both repair scopes retain validated contributions and check repaired outputs before subsequent work uses them. We evaluate \tool on 30 applications across six MAS frameworks and 9,000 tasks. It detects runtime failures with 88.28\% precision and 79.18\% recall, and achieves 84.76\% task accuracy, improving over Native execution by 26.74 percentage points and the strongest of four recovery baselines by 21.28 points. Estimated deployment token consumption is 17.92\% above Native, but 24.19\% below Reflexion and 13.05\% below Iterative Rollback. Ablation results show that combining the two repair scopes achieves higher accuracy and lower token consumption than graph-level repair alone.

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/2610.42144 — 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 2026-11-02T04:45:27.657Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).