Metraipolis › archive › dc_660a40fda0e5
RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services — arXiv:2610.41460
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41460
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:52:10.509Z
- SHA-256 of the archived text
5f508ed973c74e5366d46cd70c9c3b4a5a8bb9301d6ab73a901177abea60e2f8- Stable URL of this page
https://metraipolis.com/documento/dc_660a40fda0e5
How to cite
RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services — arXiv:2610.41460 — arXiv (en), https://arxiv.org/abs/2610.41460 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_660a40fda0e5 (Metraipolis archive dc_660a40fda0e5, sha256 5f508ed973c74e5366d46cd70c9c3b4a5a8bb9301d6ab73a901177abea60e2f8)
BibTeX
@misc{dc660a40fda0e5,
title = {RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services — arXiv:2610.41460},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41460},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_660a40fda0e5; sha256 5f508ed973c74e5366d46cd70c9c3b4a5a8bb9301d6ab73a901177abea60e2f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41460. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Web agents increasingly edit images by calling open editing models in a critique-and-retry loop, and these models differ in cost by more than an order of magnitude. After every rejected edit, a service must decide whether to retry the same model, escalate to another or give up. Existing routers pick one model per request, and cascades escalate in a fixed order. However, both treat a retry as an independent draw. We identify sticky failures, meaning that a retry after a failure succeeds only 17-53% as often as a first try across six open models, three benchmarks and two judges. Based on this finding, we propose RetryRoute, a retry-aware router that estimates each model's chance of success given the request's failure history. It plans retries, escalations and abandonment over failure states and adds live queue waits to the cost, so the same plan becomes load-aware dispatch. At the main budget, RetryRoute's success under the in-loop judge exceeds the strongest of eleven prior baselines by 2.8 points on average over eight groups. On a GPU serving testbed it raises the share of edits delivered within the service-level objective by 5.0-6.3 points over the best prior baseline at every load. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41460 — 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 2026-11-02T04:45:12.894Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).