Metraipolis › archive › dc_1c8bcbeb336b

CARE: Grounded Recursive Self-Improvement for Production Customer-Service Agents — arXiv:2611.02839

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02839
License (as archived)
CC0-1.0
Archived
2026-11-03T10:53:48.859Z
SHA-256 of the archived text
d0e2b7d4895d7ad0d2828847fe2d2be7808621c18e2c38191b450187910fc3e5
Stable URL of this page
https://metraipolis.com/documento/dc_1c8bcbeb336b

How to cite

CARE: Grounded Recursive Self-Improvement for Production Customer-Service Agents — arXiv:2611.02839 — arXiv (en), https://arxiv.org/abs/2611.02839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1c8bcbeb336b (Metraipolis archive dc_1c8bcbeb336b, sha256 d0e2b7d4895d7ad0d2828847fe2d2be7808621c18e2c38191b450187910fc3e5)
BibTeX
@misc{dc1c8bcbeb336b,
  title = {CARE: Grounded Recursive Self-Improvement for Production Customer-Service Agents — arXiv:2611.02839},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02839},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1c8bcbeb336b; sha256 d0e2b7d4895d7ad0d2828847fe2d2be7808621c18e2c38191b450187910fc3e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) in production agents involves transforming accumulated experience into reliable model updates while adapting to evolving business policies. We present CARE (Customer-service Agent Retrospective and Evolve), a grounded RSI framework that operationalizes this process in customer service. Its goal is to replace a frontier proprietary incumbent with an in-house mid-sized model that continues learning after deployment. After a one-time cold start on governed production traces, the current model serves production traffic alongside the incumbent, and its own failures drive the next update. A 24/7 inspection process establishes failures through evidence-blinded, independently reviewed judgments. Attribution separates model errors from defects in Skills, tools, or the harness, routing component failures to repair. Model-attributable trajectories are truncated at the first erroneous decision and paired with verified repairs. On-policy self-distillation (OPSD) then updates the model using the same model as teacher, with the diagnosis and repair supplied as privileged information unavailable to the student. To support continued evolution as business requirements change, training mixes failures from different Skill/SOP versions, each judged against the policy in force when it occurred. Candidates run an executable simulation test compiled from the latest SOP and then frozen, followed by offline inspection of the resulting traces. Promotion requires a combined simulation-and-inspection score at least at parity with the deployed version, confirmation through an online comparison with the incumbent, and human approval.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02839 — 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 2026-11-03T10:49:38.392Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).