{
  "abstract": "Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives---binding affinity and druggability---which single optimization steps rarely improve together. To quantify this difficulty, we introduce two diagnostic metrics: the first measures how often a single edit improves both objectives, and the second measures how often a gain on one objective comes with a loss on the other. Applying these diagnostics to current LLM-agent pipelines exposes a consistent failure mode: the agent performs molecular editing without knowing how the pocket-ligand complex responds to local modifications, thus rarely achieving joint improvement. Inspired by medicinal chemists, who probe the pocket-ligand complex with controlled analog edits before choosing an optimization direction, we propose \\textbf{PROBE}, an optimization framework built around edit--response probing. PROBE first decomposes the ligand into editable sites and builds a pocket-specific \\textbf{site map} that flags where joint gains are plausible, where the two objectives are likely in tension, and where liability substructures should be changed; it then performs controlled probe edits whose responses are distilled into an \\textbf{EditManual}. Guided by the site map and EditManual, PROBE runs an iterative multi-agent optimization loop. On the CrossDocked2020 benchmark, PROBE achieves state-of-the-art performance and substantially mitigates the failure modes exposed by our diagnostics metrics. Codes are in https://github.com/yzf-code/PROBE/tree/main",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.00555",
  "author_total": 4,
  "authors": [
    {
      "name": "Zaifei Yang"
    },
    {
      "name": "Weiyu Chen"
    },
    {
      "name": "Yaqing Wang"
    },
    {
      "name": "James Kwok"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3m6jh4raxamg1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.00555",
  "fulltext_url": null,
  "id": "3m6jh4raxamg1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.00555",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7163214544",
  "pdf_url": "https://arxiv.org/pdf/2606.00555",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3m6jh4raxamg1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:20Z",
      "native_id": "2606.00555",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.00555"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design",
  "title_text": "Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:20Z",
  "url": "https://research.draconitic.com/paper/3m6jh4raxamg1",
  "venue": "arXiv",
  "versions": []
}