{
  "abstract": "Organic synthesis is a multi-round campaign, not a one-shot SMILES completion: a failed solvent, a poisoned catalyst, or leftover starting-material peaks in the 1H NMR force the chemist to revise conditions and try again. Tool-using chemistry agents and condition classifiers still emit a single recipe and then stop. We propose CampChem, an adaptive campaign agent built on a chemistry-instruction LLM. A longitudinal campaign adaptive planner (LCAP) keeps a short memory of failed condition slots and peak signatures and decodes the next catalyst/solvent/reagent tuple under a mask. Chemistry rubric-as-judge reinforcement learning (Chem-RaJ) scores stoichiometry, hazard compatibility, slot completeness, and spectral consistency instead of using a free-form LLM judge. A residual spectral booster (RSB) injects a permutation-invariant peak-set residual when NMR is available and gates to zero otherwise. On SMolInstruct, CampChem reaches 67.1% forward-synthesis and 36.1% retrosynthesis Top-1 exact match with a Mistral-7B LoRA backbone. On USPTO-Condition it attains 0.2940 overall Top-1, and on AutoLabs Experiment 5 it raises protocol F1 from 0.75 to 0.81. Ablations show that Chem-RaJ carries most of the spectrum-free gain, LCAP matters once a prior tuple has been rejected, and RSB contributes mainly on simulated NMR revision.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Zixuan Shi",
      "orcid": "0009-0004-8390-8942"
    },
    {
      "name": "Mengyao Qian"
    },
    {
      "name": "Yichao Sun"
    },
    {
      "name": "Haotian Gu"
    },
    {
      "name": "Jiarui Feng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4mxt4gvs3bdpa.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008453/v1",
  "fulltext_url": null,
  "id": "4mxt4gvs3bdpa",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008453/v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7211933006",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008453/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/4mxt4gvs3bdpa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008453",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008453/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "CampChem: Rubric-Grounded Adaptive Campaigns for Multi-Round Organic Synthesis with Residual Spectral Observation",
  "title_text": "CampChem: Rubric-Grounded Adaptive Campaigns for Multi-Round Organic Synthesis with Residual Spectral Observation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/4mxt4gvs3bdpa",
  "venue": "ChemRxiv",
  "versions": []
}