Original Paper: https://arxiv.org/abs/2408.08435
By: Shengran Hu, Cong Lu, Jeff Clune
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.
Figure: Overview of the proposed algorithm Meta Agent Search and examples of discovered agents. In our algorithm, we instruct the “meta” agent to iteratively program new agents, test their performance on tasks, add them to an archive of discovered agents, and use this archive to inform the meta agent in subsequent iterations. We show three example agents across our runs, with all names generated by the meta agent. The detailed code of example agents can be found in Appendix F.
Imagine a world where intelligent systems can design themselves, evolving iteratively to solve increasingly complex tasks. This is not merely the stuff of science fiction but the reality being brought to life by researchers Shengran Hu, Cong Lu, and Jeff Clune.
Their latest research paper introduces a groundbreaking approach to the automatic design of agentic systems, aptly named Automated Design of Agentic Systems (ADAS).
This innovative methodology leverages a meta agent to create, test, and refine new agents, pushing the boundaries of what's possible in artificial intelligence (AI).
The core of ADAS lies in its ability to automate the design of agentic systems through a meta agent, which essentially acts as an AI architect. The process is encapsulated in an algorithm called Meta Agent Search. Here’s a breakdown of how it works: