用贝叶斯推理生成工作流，准确率最高提升9个百分点。
BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation
- 将工作流生成建模为贝叶斯推断，分步采样并动态优化。
- 在6个数据集上比当前最优方法准确率高最多9个百分点。
- 无需训练，适合需要可解释性的工作流设计场景。
自动工作流生成是指为复杂端到端任务自动生成一系列LLM调用、工具调用和后处理步骤的过程。现有方法多将其视为缺乏理论基础的优化问题。本文提出将工作流生成建模为对工作流后验分布的贝叶斯推断，并引入 extbf{贝叶斯工作流生成（BWG）}——一种基于并行前瞻回溯进行重要性加权、再通过序列内迭代优化器实现全局改进的采样框架。我们证明，在无优化器的情况下，加权经验分布会收敛至目标后验。我们将BWG实例化为 extbf{BayesFlow}，一种无需训练的工作流构建算法。在六个基准数据集上，BayesFlow相比当前最优基线准确率最高提升9个百分点，相比零样本提示提升高达65个百分点，验证了BWG作为基于搜索的工作流设计的原理性升级。代码将开源于https://github.com/BoYuanVisionary/BayesFlow。
原文摘要 · Abstract (English)
Automatic workflow generation is the process of automatically synthesizing sequences of LLM calls, tool invocations, and post-processing steps for complex end-to-end tasks. Most prior methods cast this task as an optimization problem with limited theoretical grounding. We propose to cast workflow generation as Bayesian inference over a posterior distribution on workflows, and introduce \textbf{Bayesian Workflow Generation (BWG)}, a sampling framework that builds workflows step-by-step using parallel look-ahead rollouts for importance weighting and a sequential in-loop refiner for pool-wide improvements. We prove that, without the refiner, the weighted empirical distribution converges to the target posterior. We instantiate BWG as \textbf{BayesFlow}, a training-free algorithm for workflow construction. Across six benchmark datasets, BayesFlow improves accuracy by up to 9 percentage points over SOTA workflow generation baselines and by up to 65 percentage points over zero-shot prompting, establishing BWG as a principled upgrade to search-based workflow design. Code will be available on https://github.com/BoYuanVisionary/BayesFlow.
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。