{
  "id": 6455,
  "url": "https://arxiv.org/abs/2604.21937v2",
  "title": "MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization",
  "summary": "Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, screening, and optimization. It unifies over 30 specialized domain resources through a three-tier hierar",
  "authors": "Lisheng Zhang, Lilong Wang, Xiangyu Sun, Wei Tang, Haoyang Su, Yuehui Qian et al.",
  "category": "research",
  "topics": "healthcare,agents-autonomy,biotech",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-02T09:27:36.000Z",
  "fetched_at": "2026-07-14T16:32:28.613Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6455",
  "original_url": "https://arxiv.org/abs/2604.21937v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}