Metraipolis › archive › dc_524d0a5c19e1

Route Before Response: Fail-Closed Routing for LLM-Enabled Customer-Service Software — arXiv:2611.07534

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07534
License (as archived): CC0-1.0
Archived: 2026-11-06T14:51:28.590Z
SHA-256 of the archived text: 8141a37710ed825aba9a8ec88db591ad11d61f6b968acd3e633c6f9306a3a6fd
Stable URL of this page: https://metraipolis.com/documento/dc_524d0a5c19e1

How to cite

Route Before Response: Fail-Closed Routing for LLM-Enabled Customer-Service Software — arXiv:2611.07534 — arXiv (en), https://arxiv.org/abs/2611.07534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_524d0a5c19e1 (Metraipolis archive dc_524d0a5c19e1, sha256 8141a37710ed825aba9a8ec88db591ad11d61f6b968acd3e633c6f9306a3a6fd)

BibTeX

@misc{dc524d0a5c19e1,
  title = {Route Before Response: Fail-Closed Routing for LLM-Enabled Customer-Service Software — arXiv:2611.07534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_524d0a5c19e1; sha256 8141a37710ed825aba9a8ec88db591ad11d61f6b968acd3e633c6f9306a3a6fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-enabled customer-service software in financial institutions must choose a downstream service before responding. Classifiers and LLM routers can identify a relevant label or destination, but a composed application must still verify dispatch permission and entity registration. We study this integration problem as boundary-aware pre-response routing. We present RouteBR, a controller in which one model call proposes a primary service action and registered object, then deterministic code checks identifiers and versioned rules before dispatch or a specified non-dispatch outcome. Lower-ranked candidates cannot replace a blocked primary route. We construct 600 privacy-preserving scenarios from recurring confidential-request patterns at a real financial institution; three engineers jointly reviewed the scenarios and labels. On the 200-case CONFIRM MAIN split, RouteBR reaches 97.5% final-path exact match. A matched one-call baseline given the same rules reaches 95.5%, whereas a diagnostic baseline without the rule program obtains 94.0% action accuracy but only 41.0% final-path exact match. Across 166 non-dispatch MAIN and FLIP cases, RouteBR produces no false dispatch. The artifact pairs all 1,960 prediction rows with raw receipts while excluding gold and reviewer fields from model requests. These results support separating model proposals from code-owned, replayable execution. Our implementation is available at 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/2611.07534 — 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 2026-11-06T14:21:57.531Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).