Metraipolis › archive › dc_ef4037863530

Principled Human-AI Collaboration in Agentic Workflows — arXiv:2611.01566

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01566
License (as archived)
CC0-1.0
Archived
2026-11-03T10:56:45.303Z
SHA-256 of the archived text
d94677344b80ee8abcd4fbc85024da874ceef134110a5549c918bc315d966210
Stable URL of this page
https://metraipolis.com/documento/dc_ef4037863530

How to cite

Principled Human-AI Collaboration in Agentic Workflows — arXiv:2611.01566 — arXiv (en), https://arxiv.org/abs/2611.01566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef4037863530 (Metraipolis archive dc_ef4037863530, sha256 d94677344b80ee8abcd4fbc85024da874ceef134110a5549c918bc315d966210)
BibTeX
@misc{dcef4037863530,
  title = {Principled Human-AI Collaboration in Agentic Workflows — arXiv:2611.01566},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01566},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef4037863530; sha256 d94677344b80ee8abcd4fbc85024da874ceef134110a5549c918bc315d966210},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Organizations adopting AI face the challenge of deciding which outputs can be released without human review while meeting the quality standards of human experts. We develop a statistical framework for delegating tasks between experts and black-box generate-verify workflows, in which AI-generated answers are verified and revised over multiple rounds. Before deployment, human experts evaluate selected outputs, and their judgments are used to calibrate the verifier threshold and number of attempts. Our method selects the policy with the highest estimated automation rate among statistically approved candidates, without modifying the generator or verifier. We establish finite-sample control of the error rate among released outputs, characterize the expert evaluations sufficient to attain a target automation rate, and derive a minimax lower bound establishing rate optimality in the quality margin and required confidence. In a MultiHiertt financial question-answering case study, average held-out automation increases from 2.50% to 24.17% as expert evaluations accumulate, while released-output error rates remain around 1.20%. In contrast, heuristics that release answers after consistently high verifier scores either violate the 5% error tolerance or automate at most 1.30% of tasks. Synthetic experiments further examine these theoretical predictions under controlled settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2611.01566 — 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 2026-11-03T10:49:38.567Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).