@inproceedings{ge-etal-2026-protocycle,
    title = "{P}roto{C}ycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design",
    author = "Ge, Yutang  and
      Zhao, Guojiang  and
      Li, Sihang  and
      Cheng, Zheng  and
      Zhao, Zifeng  and
      Xia, Hanchen  and
      Ke, Guolin  and
      Zhang, Linfeng  and
      Gao, Zhifeng  and
      Wang, Yu Guang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.763/",
    pages = "15562--15586",
    ISBN = "979-8-89176-395-1",
    abstract = "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 multi-round, feedback-driven decision cycle. ProtoCycle couples an LLM planner with a lightweight tool environment designed to emulate the iterative workflow of human protein engineers and uses LLM-driven reflection on tool feedback to revise plans. Trained with supervised trajectories and online reinforcement learning, ProtoCycle achieves strong language alignment while maintaining competitive foldability, and ablations show that reflection substantially improves sequence quality."
}