{
  "abstract": "We study a human-AI service system in which tasks arrive sequentially and are processed through a two-stage architecture: an automated chatbot followed, when necessary, by a human agent. We consider $T$ sequentially arriving tasks, each belonging to one of $K$ heterogeneous types. For each task the decision maker chooses how many resources to allocate to the chatbot, whose type-dependent success probabilities are initially unknown. Tasks not resolved by the chatbot enter type-dependent human-service queues, where they are processed by a human agent with unknown service rates. This model captures a central tradeoff in hybrid service systems: relying more on automation reduces human congestion but increases chatbot costs, while insufficient automation may overload the human agent. We propose the UCB-DPP policy, which combines Upper Confidence Bounds with Drift-Plus-Penalty control to learn the unknown parameters of the system while making queue-aware decisions. We prove that UCB-DPP achieves regret $\\widetilde{\\mathcal{O}}(K\\sqrt{T})$ and guarantees mean-rate stability of the human-service queues. Simulations on synthetic instances show that the proposed policy outperforms natural baselines.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.06017",
  "author_total": 3,
  "authors": [
    {
      "name": "Giovanni Montanari"
    },
    {
      "name": "Marco Scarsini"
    },
    {
      "name": "Vianney Perchet"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9a20h8taby4nh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.06017",
  "fulltext_url": null,
  "id": "9a20h8taby4nh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.06017",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1404|Advanced Queuing Theory Analysis"
    ]
  ],
  "openalex": "W7167711098",
  "pdf_url": "https://arxiv.org/pdf/2607.06017",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9a20h8taby4nh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:22Z",
      "native_id": "2607.06017",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.06017"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Learning When to Automate: Queue Control in Human-AI Service Systems",
  "title_text": "Learning When to Automate: Queue Control in Human-AI Service Systems",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:22Z",
  "url": "https://research.draconitic.com/paper/9a20h8taby4nh",
  "venue": "arXiv",
  "versions": []
}