Lune

ACL Findings2026

Evolving Agentic Workflow Driven by Human-Agent Collaboration

Yuxin Liu, Jinxuan Zhang, Yuezhang Peng, Hefeng Zhou, Xiangfeng Wang, Jiong Lou, Chentao Wu, Jie Li, Jingjing Qu, Chaochao Lu

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 o1preview 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Reflexion: language agents with verbal reinforcement learning cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on19

  1. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  2. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  3. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  4. Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
  5. ALFWorld: Aligning Text and Embodied Environments for Interactive LearningMohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk et al.ICLR 2021 · 819 citations

Related papers

  1. AFlow: Automating Agentic Workflow GenerationJiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng et al.ICLR 2025
  2. DyFlow: Dynamic Workflow Framework for Agentic ReasoningYanbo Wang, Zixiang Xu, Yue Huang, Xiangqi Wang et al.NeurIPS 2025 · 24 citations
  3. A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction OperatorsMingming Zhao, Xiaokang Wei, Yuanqi Shao, Kaiwen Zhou et al.AAAI 2026
  4. AdaptFlow: Adaptive Workflow Optimization via Meta-LearningRunchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang et al.EMNLP Findings 2025 · 1 citation
  5. FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow GenerationXiang Wang, Zongtao Yang, Zhuojian Hong, Shuhao Zhang et al.ACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines