{
  "abstract": "NMR time and a shared liquid-handling robot are scarce, noisy and only partially observable, so the practical question is which experiment to run next on which instrument. Existing reaction-optimisation benchmarks measure budgets in experiments rather than instrumenthours, and they learn chemical feasibility only by paying for infeasible runs. We present CHASE, a centralised-training decentralised-execution scheduler with three coupled modules: a belief encoder (PEB) infers per-instrument throughput and channel health from local event histories and exchanges only low-bandwidth summaries; a chemistry feasibility gate (CFG) masks chemically impossible actions with a four-layer compatibility graph; and a counterfactual attribution module (CFA) converts delayed campaign reward into per-step credit through leave-one-experiment-out surrogate scoring. On the Buchwald–Hartwig (3,955 reactions) and Suzuki–Miyaura (5,760 nanomole-scale conditions) HTE datasets, the ten Olympus benchmarks and a plant-wide Tennessee Eastman process, CHASE reaches 94.1% best-found yield under a shared 60 instrument-hour budget, +3.3 points over the strongest same-setting baseline, attains 90% of the attainable optimum with 25.6% fewer experiments, and cuts infeasible actions to 0.7–1.6% across plate, flow and fault-injection settings.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Yuhang Shao",
      "orcid": "0009-0008-9000-8052"
    },
    {
      "name": "Siqi Meng"
    },
    {
      "name": "Yutian Luo"
    },
    {
      "name": "Jiawei Tan"
    },
    {
      "name": "Chengyu He"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/740z8g0aad4dv.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010837/v1",
  "fulltext_url": null,
  "id": "740z8g0aad4dv",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010837/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7223178190",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010837/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/740z8g0aad4dv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:24Z",
      "native_id": "10.26434/chemrxiv.15010837",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010837/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Multi-Agent Scheduling of Instrument-Time for High-Throughput Palladium-Catalysed Cross-Coupling",
  "title_text": "Multi-Agent Scheduling of Instrument-Time for High-Throughput Palladium-Catalysed Cross-Coupling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:24Z",
  "url": "https://research.draconitic.com/paper/740z8g0aad4dv",
  "venue": "ChemRxiv",
  "versions": []
}