Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
This is a vision paper that outlines a paradigm shift for scientific researchers, but it is incremental as it builds on existing LLM and agent concepts without introducing new methods.
The paper examines the role of large language model-based autonomous agents in accelerating scientific discovery by orchestrating interactions with scientists, language, code, and physics across the discovery lifecycle, highlighting their transformative potential but without providing concrete numerical results.
Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.