SR-Scientist: Scientific Equation Discovery With Agentic AI
This addresses the challenge of automating scientific discovery for researchers by integrating LLMs more deeply into the equation discovery process, representing a novel method rather than an incremental improvement.
The paper tackles the problem of scientific equation discovery by elevating LLMs from simple equation proposers to autonomous AI scientists that write code, implement equations, and optimize them based on experimental feedback, resulting in performance improvements of 6% to 35% over baselines across four science disciplines.
Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as code, submits it for evaluation, and optimizes the equation based on experimental feedback. Specifically, we wrap the code interpreter into a set of tools for data analysis and equation evaluation. The agent is instructed to optimize the equation by utilizing these tools over a long horizon with minimal human-defined pipelines. Empirical results show that SR-Scientist outperforms baseline methods by an absolute margin of 6% to 35% on datasets covering four science disciplines. Additionally, we demonstrate our method's robustness to noise, the generalization of the discovered equations to out-of-domain data, and their symbolic accuracy. Furthermore, we develop an end-to-end reinforcement learning framework to enhance the agent's capabilities.