Metraipolis › archive › dc_436ec41e0dbc

Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents — arXiv:2610.02503

Source
arXiv
Original
https://arxiv.org/abs/2610.02503
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:03.823Z
SHA-256 of the archived text
1169c1971749bf73211a69f5623e3beba59cdb12ead60a76d2252ade19a1feb9
Stable URL of this page
https://metraipolis.com/documento/dc_436ec41e0dbc

How to cite

Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents — arXiv:2610.02503 — arXiv, https://arxiv.org/abs/2610.02503 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_436ec41e0dbc (Metraipolis archive dc_436ec41e0dbc, sha256 1169c1971749bf73211a69f5623e3beba59cdb12ead60a76d2252ade19a1feb9)
BibTeX
@misc{dc436ec41e0dbc,
  title = {Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents — arXiv:2610.02503},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02503},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_436ec41e0dbc; sha256 1169c1971749bf73211a69f5623e3beba59cdb12ead60a76d2252ade19a1feb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02503. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying compound AI systems reliably and safely requires understanding failure modes that emerge at component boundaries, not within individual models. Cascading errors propagate across component boundaries, silent quality degradation evades standard monitoring, and coordination failures yield incorrect collective behavior from individually correct parts. We analyze 150 production incident reports from open-source compound AI projects and anonymized enterprise deployments to construct a taxonomy of 23 failure modes organized into five categories: retrieval failures, generation failures, tool failures, orchestration failures, and integration failures. For each category, we propose resilience patterns with measured effectiveness from controlled fault injection experiments. Circuit breakers reduce cascade propagation by 89%, output quality gates catch 73% of silent degradation before user impact, and component isolation reduces blast radius by 64%. Systems implementing three or more resilience patterns from our catalog reduce mean-time-to-recovery (MTTR) by 71% compared to unstructured monitoring baselines. We release the incident taxonomy and pattern catalog as a practitioner resource.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02503 — 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 2026-10-05T22:45:55.763Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).