Metraipolis › archive › dc_40ac718744db

Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection — arXiv:2610.18881

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.18881
License (as archived)
CC0-1.0
Archived
2026-10-15T14:21:04.602Z
SHA-256 of the archived text
8c9b9b5556a41dbcfe44d42ce85438a7c2ae0c3b4b3d499e672af87f93141a57
Stable URL of this page
https://metraipolis.com/documento/dc_40ac718744db

How to cite

Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection — arXiv:2610.18881 — arXiv (en), https://arxiv.org/abs/2610.18881 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40ac718744db (Metraipolis archive dc_40ac718744db, sha256 8c9b9b5556a41dbcfe44d42ce85438a7c2ae0c3b4b3d499e672af87f93141a57)
BibTeX
@misc{dc40ac718744db,
  title = {Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection — arXiv:2610.18881},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.18881},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40ac718744db; sha256 8c9b9b5556a41dbcfe44d42ce85438a7c2ae0c3b4b3d499e672af87f93141a57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.18881. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a conversational flow set by law. In debt collection, it must confirm it is speaking to the debtor before mentioning the debt, identify itself and the creditor, state the amount, and avoid prohibited language. Every creditor turns these rules into its own procedure and revises it. We ask whether a small, self-hosted policy can be trained once and then follow regulated procedures it has never seen. One machine-readable specification per deployment, FlowSpec, generates the policy instruction, gates the tools, supplies the supervision and defines the tests; the agent speaks only approved catalogue sentences. We fine-tune a 9-billion-parameter model on 2,506 conversations from 297 randomized procedures and evaluate a Thai outbound-call agent on four unseen deployment procedures (three debt collection, one non-debt), one from a wholly withheld lineage. Documented checks, fixed by the procedure, rise from 67--71 percents to 93--100 percents, while grounded checks, fixed by the conversation, already pass at 97--100 percents before training; scenario pass rate rises from 15/43 to 40/43. An audit of the shared specification finds 11 defects, 3 of which its own metric did not expose.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.18881 — 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 2026-10-15T13:53:35.787Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).