本文介绍了一个名为自动设计智能体系统 (ADAS) 的新研究领域，旨在自动创建强大的智能体系统设计，包括发明新的构建模块或以新的方式组合它们。研究人员提出了一种新方法，即通过代码定义智能体，并由元智能体自动发现新的智能体，从而在代码中编程出更好的智能体。这项研究表明，元智能体搜索算法能够逐步发明出具有新颖设计的智能体，这些智能体在多个领域（包括编码、科学和数学）中都优于最先进的手工设计智能体。

🤔 **自动设计智能体系统 (ADAS)**：这项研究提出了一个新领域，旨在自动创建强大的智能体系统设计，包括发明新的构建模块或以新的方式组合它们。与传统的依赖于手工设计解决方案的机器学习方法不同，ADAS 旨在通过自动学习来找到最佳的智能体系统设计。

🤖 **代码定义智能体**：研究人员提出了一种新方法，即通过代码定义智能体，并由元智能体自动发现新的智能体，从而在代码中编程出更好的智能体。这种方法利用编程语言的图灵完备性，理论上可以学习任何可能的智能体系统，包括新颖的提示、工具使用、控制流程以及它们的组合。

🚀 **元智能体搜索算法**：研究人员开发了一种名为元智能体搜索的简单而有效的算法，该算法通过迭代地编程新的智能体，并基于不断增长的先前发现的档案来实现。实验结果表明，该算法能够逐步发明出具有新颖设计的智能体，这些智能体在多个领域（包括编码、科学和数学）中都优于最先进的手工设计智能体。

🏆 **跨领域和模型的鲁棒性**：研究人员发现，由元智能体搜索发明的智能体在跨领域和模型转移时仍能保持优异的性能，这表明它们具有鲁棒性和通用性。

🌟 **未来的可能性**：这项研究表明，自动设计智能体系统具有巨大的潜力，可以帮助人类创造出更强大、更智能的智能体，解决更多复杂的问题。

Published on August 19, 2024 11:06 PM GMT

Authors: Shengran Hu, Cong Lu, Jeff Clune.

Brief summary: proof of concept of automated LM scaffolding design, with state-of-the-art performance on several tasks. 

Website: https://www.shengranhu.com/ADAS/. 

X/twitter summary thread: https://x.com/jeffclune/status/1825551351746867502. 

Abstract:

Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine learning teaches us that hand-designed solutions are eventually replaced by learned solutions. We formulate a new research area, Automated Design of Agentic Systems (ADAS), which aims to automatically create powerful agentic system designs, including inventing novel building blocks and/or combining them in new ways. We further demonstrate that there is an unexplored yet promising approach within ADAS where agents can be defined in code and new agents can be automatically discovered by a meta agent programming ever better ones in code. Given that programming languages are Turing Complete, this approach theoretically enables the learning of any possible agentic system: including novel prompts, tool use, control flows, and combinations thereof. We present a simple yet effective algorithm named Meta Agent Search to demonstrate this idea, where a meta agent iteratively programs interesting new agents based on an ever-growing archive of previous discoveries. Through extensive experiments across multiple domains including coding, science, and math, we show that our algorithm can progressively invent agents with novel designs that greatly outperform state-of-the-art hand-designed agents. Importantly, we consistently observe the surprising result that agents invented by Meta Agent Search maintain superior performance even when transferred across domains and models, demonstrating their robustness and generality. Provided we develop it safely, our work illustrates the potential of an exciting new research direction toward automatically designing ever-more powerful agentic systems to benefit humanity.

 

Discuss