@inproceedings{liu-etal-2026-evolving,
    title = "Evolving Agentic Workflow Driven by Human-Agent Collaboration",
    author = "Liu, Yuxin  and
      Zhang, Jinxuan  and
      Peng, Yuezhang  and
      Zhou, Hefeng  and
      Wang, Xiangfeng  and
      Lou, Jiong  and
      Wu, Chentao  and
      LI, Jie  and
      Qu, Jingjing  and
      Lu, Chaochao",
    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.1250/",
    pages = "24960--24969",
    ISBN = "979-8-89176-395-1",
    abstract = "Agentic workflows, composed of multiple collaborating Large Language Models (LLMs), have become a key paradigm for complex problem-solving. However, their effectiveness is often hindered by three critical challenges: high manual design costs, inefficient agentic search, and poor dynamic adaptability to new tasks and human preferences. To address these limitations, we propose HFlow, an evolutionary framework for generating agentic workflows through human-agent collaboration. HFlow employs an evolutionary algorithm to automate the search for optimal workflows by mutating and crossing over their structures, prompts, and LLM backbones. This process is guided by human preferences to ensure rapid convergence, while a hierarchical experience memory enables the generalization of learned strategies. Extensive experiments on math and code generation benchmarks show HFlow surpasses other automated baselines by up to 27.34{\%}, while achieving comparable performance to o1-preview at only one-fourth of the cost. Our work introduces a new paradigm for workflow design that produces cost-effective and adaptive solutions, better aligning automated agentic systems with dynamic human needs."
}