- author = "Shijie Xia and Yuhan Sun and Pengfei Liu",
- title = "{SR-Scientist}: Scientific Equation Discovery With {Agentic AI}",
- booktitle = "Proceedings of the 43rd International Conference on Machine Learning",
- year = "2026",
- editor = "Alekh Agarwal and Miro Dudik and Martin Jaggi and Sharon Li",
- address = "Seoul, South Korea",
- month = jul # " 6-11",
- keywords = "genetic algorithms, genetic programming, GPLearn, PySR, uDSR, llm-srbench, verl, LLM, AI",
-
URL = "
https://icml.cc/virtual/2026/73599",
-
URL = "https://arxiv.org/abs/2510.11661",
-
code_url = "https://github.com/GAIR-NLP/SR-Scientist",
- size = "25 pages",
- abstract = "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 using 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 percent to 35 percent 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.",
-
notes = "'We conduct RL training on 32 NVIDIA H200 GPUs.'
ICML 2026 https://icml.cc/virtual/2026",
