Agent Laboratory: Using LLM Agents as Research Assistants
Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, Emad Barsoum
2025-01-09
Summary
This paper talks about Agent Laboratory, a new AI system that helps scientists do research faster and more efficiently by automating many parts of the research process.
What's the problem?
Scientific research takes a lot of time and money, which limits how many ideas scientists can explore. This slows down new discoveries and makes research expensive.
What's the solution?
The researchers created Agent Laboratory, an AI system that can do much of the research work on its own. It uses advanced language models to read scientific papers, run experiments, and write reports. Scientists can give it an idea to research, and then guide it or give feedback at different stages. The team tested Agent Laboratory with different AI models and asked researchers to evaluate its work.
Why it matters?
This matters because it could make scientific research much faster and cheaper. Scientists could explore more ideas and focus on being creative instead of doing time-consuming tasks. Agent Laboratory was able to do high-quality research work while cutting costs by 84% compared to other methods. This could lead to more scientific discoveries and innovations in less time, potentially speeding up progress in many fields of study.
Abstract
Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research quality, we introduce Agent Laboratory, an autonomous LLM-based framework capable of completing the entire research process. This framework accepts a human-provided research idea and progresses through three stages--literature review, experimentation, and report writing to produce comprehensive research outputs, including a code repository and a research report, while enabling users to provide feedback and guidance at each stage. We deploy Agent Laboratory with various state-of-the-art LLMs and invite multiple researchers to assess its quality by participating in a survey, providing human feedback to guide the research process, and then evaluate the final paper. We found that: (1) Agent Laboratory driven by o1-preview generates the best research outcomes; (2) The generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; (3) Human involvement, providing feedback at each stage, significantly improves the overall quality of research; (4) Agent Laboratory significantly reduces research expenses, achieving an 84% decrease compared to previous autonomous research methods. We hope Agent Laboratory enables researchers to allocate more effort toward creative ideation rather than low-level coding and writing, ultimately accelerating scientific discovery.