MoFlow: Multi-Objective Agentic Workflow Generation

MoFlow：多目标智能体工作流生成

Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Existing methods for workflow generation typically optimize accuracy alone or a weighted sum of objectives, so each trained generator commits to one fixed trade-off and must be retrained from scratch when preferences change. 摘要： 我们研究了旨在联合优化多个目标（如准确性、成本、延迟、鲁棒性和一致性）的智能体工作流生成技术。现有的工作流生成方法通常仅优化准确性或目标的加权和，因此每个训练好的生成器都局限于一种固定的权衡方案，一旦偏好发生变化，就必须从头开始重新训练。

To alleviate this, we propose MoFlow, which generates workflows optimized across varied preferences. Specifically, MoFlow formulates workflow generation as a multi-objective Markov decision process and solves it by leveraging Convex-Hull Monte Carlo Tree Search with optimistic set-valued backups, where every node stores a set of reachable trade-offs rather than one weighted score. 为了解决这一问题，我们提出了 MoFlow，它能够生成针对不同偏好进行优化的工作流。具体而言，MoFlow 将工作流生成建模为一个多目标马尔可夫决策过程，并通过利用带有乐观集值回溯（optimistic set-valued backups）的凸包蒙特卡洛树搜索（Convex-Hull Monte Carlo Tree Search）来求解。在该方法中，每个节点存储的是一组可达到的权衡方案，而非单一的加权分数。

A single search thus approximately covers the Pareto front, from which MoFlow can return a workflow for any preference by lookup without retraining. We evaluate MoFlow against six strong baselines on six benchmarks spanning mathematics, code, and question answering. 因此，单次搜索即可近似覆盖帕累托前沿（Pareto front），MoFlow 可以通过查找直接返回满足任何偏好的工作流，而无需重新训练。我们在涵盖数学、代码和问答的六个基准测试上，将 MoFlow 与六个强基线模型进行了对比评估。

Since the baselines are single-scalar optimizers by design, an apples-to-apples comparison is difficult. We instead adopt an evaluation setup that favors the baselines, in that they are rerun for each testing preference, which MoFlow never sees. Even under this stringent setup, MoFlow achieves the highest average hypervolume. 由于基线模型在设计上属于单标量优化器，因此很难进行直接的公平比较。我们采取了一种对基线模型更有利的评估设置，即针对每个测试偏好重新运行基线模型，而 MoFlow 则无需此类操作。即便在如此严苛的设置下，MoFlow 依然实现了最高的平均超体积（hypervolume）。