{
  "id": 5696,
  "url": "https://arxiv.org/abs/2604.16896v1",
  "title": "ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design",
  "summary": "Designing proteins that satisfy natural language functional requirements is a central goal in protein engineering. A straightforward baseline is to fine-tune generic instruction-tuned LLMs as direct text-to-sequence generators, but this is data- and compute-hungry. With limited supervision, LLMs can produce coherent plans in text yet fail to reliably realize them as sequences. This plan-execute gap motivates ProtoCycle, an agentic framework for protein design that uses LLMs primarily to drive a ",
  "authors": "Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia et al.",
  "category": "research",
  "topics": "agents-autonomy,biotech",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-18T08:09:10.000Z",
  "fetched_at": "2026-07-14T16:31:57.533Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5696",
  "original_url": "https://arxiv.org/abs/2604.16896v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}