AgentFactory: Towards Automated Agentic System Design and Optimization
作者: Enci Zhang, Haofeng Wang, Yuesheng Zhu, Xiaole Cui, Guibo Luo
分类: cs.AI
发布日期: 2026-09-01
💡 一句话要点
提出AgentFactory以解决自动化智能系统设计与优化问题
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 智能系统 自动化优化 大型语言模型 工作流设计 多目标优化
📋 核心要点
- 现有方法在设计和优化智能系统时过于依赖人工，缺乏适应性和可扩展性，未能充分考虑模型能力和实际部署约束。
- AgentFactory框架通过联合优化基础模型和工作流结构，采用三阶段优化流程，自动发现有效的模型与工作流组合。
- 实验结果显示，AgentFactory在多个领域的基准测试中均优于手动设计和现有自动化方法，平均提升9.1%，在医学和金融领域的任务中提升尤为显著。
📝 摘要（中文）
大型语言模型（LLMs）在智能系统中展现出强大的推理和复杂任务执行能力。然而，现有的手动设计和优化智能系统的方法过于依赖人工，限制了其适应性和可扩展性。本文提出了AgentFactory框架，能够同时优化基础模型和工作流结构，考虑性能、成本和效率等多个目标。AgentFactory利用先进的LLMs作为优化器，通过三阶段优化流程自动发现有效的模型和工作流组合。实验结果表明，AgentFactory在八个基准测试中表现优异，平均提升9.1%，在特定领域任务中更是取得显著进展。
🔬 方法详解
问题定义：本文旨在解决现有智能系统设计与优化方法过于依赖人工的问题，导致适应性和可扩展性不足，且未能充分考虑模型能力和实际部署约束。
核心思路：AgentFactory框架的核心思路是通过联合优化基础模型和工作流结构，利用大型语言模型作为优化器，自动探索和评估不同的智能系统设计，以适应特定任务需求。
技术框架：AgentFactory的整体架构包括三个主要阶段：首先，定义优化目标和约束；其次，利用LLMs进行搜索和评估；最后，迭代优化以发现最佳配置。
关键创新：AgentFactory的创新在于其能够同时优化模型和工作流结构，并考虑多个目标，显著提高了智能系统的性能和效率，与传统方法相比具有本质区别。
关键设计：在设计中，AgentFactory设置了多个优化目标，包括性能、成本和效率，采用了适应性损失函数和多层次网络结构，以确保优化过程的有效性和灵活性。
🖼️ 关键图片
📊 实验亮点
在八个基准测试中，AgentFactory的平均性能提升达9.1%，在医学领域的MedQA任务中提升19.6%，在金融领域的FinEval任务中提升18.7%。这些结果表明AgentFactory在特定领域任务中具有显著优势，超越了手动设计和现有自动化方法。
🎯 应用场景
AgentFactory框架具有广泛的应用潜力，适用于需要高效智能系统的多个领域，如医疗、金融、编程和数学等。通过自动化优化，能够显著提升系统的性能和适应性，降低人工干预的需求，推动智能系统的普及与发展。
📄 摘要（原文）
Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization.