让智能体自动设计并修复复杂任务流程，无需人工干预。
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
- 用可执行的流程画布环境实现每步编辑的语法检查反馈。
- 通过强化学习训练轻量级智能体，逐步完成流程构建并修复错误。
- 支持多种工具库和大模型，适用于复杂任务自动化场景。
近年来，智能体工作流被广泛应用于解决复杂人类任务。然而，现有工作流构建仍面临三大挑战：依赖人工设计、缺乏图层级执行反馈，以及在长周期构建中无法实时修复错误。为此，我们提出 FlowSteer，一种智能体自主设计智能体工作流的新范式——单个智能体端到端生成下游执行器运行的工作流。为支持该范式，我们引入工作流画布（Workflow Canvas），一种新型可执行图状态环境，对每次原子编辑返回语法校验后的执行反馈。基于画布，我们进一步提出强化渐进式画布编辑方法，其中轻量级策略智能体根据实时画布反馈，每轮发起一次原子编辑，并通过强化学习端到端训练。此外，FlowSteer 提供即插即用框架，支持多样化的操作符库与可替换的大语言模型后端。在十二个数据集上的实验表明，FlowSteer 在各类任务中显著优于基线。代码已公开于 https://anonymous.4open.science/r/FlowSteer-9B2E。
原文摘要 · Abstract (English)
In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution feedback, and the inability to repair errors in-loop during long-horizon construction. To address these challenges, we propose FlowSteer, a new paradigm of Agent Designing Agentic Workflows - a single agent itself end-to-end designs the workflow that a downstream executor runs. To support this paradigm, we introduce the Workflow Canvas, a novel executable graph-state environment that returns syntax-checked execution feedback for every atomic edit. Built on the canvas, we further propose Reinforced Progressive Canvas Editing, in which a lightweight policy agent issues one atomic edit per turn conditioned on real canvas feedback, and is trained end-to-end via reinforcement learning. Moreover, FlowSteer provides a plug-and-play framework that supports diverse operator libraries and interchangeable LLM backends. Experimental results on twelve datasets show that FlowSteer significantly outperforms baselines across various tasks. Our code is available at https://anonymous.4open.science/r/FlowSteer-9B2E.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。