Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.12259 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917293158563840 |
|---|---|
| author | Yang, Jianke Venkatachalam, Ohm Kianezhad, Mohammad Vadgama, Sharvaree Yu, Rose |
| author_facet | Yang, Jianke Venkatachalam, Ohm Kianezhad, Mohammad Vadgama, Sharvaree Yu, Rose |
| contents | Explaining observed phenomena through symbolic, interpretable formulas is a fundamental goal of science. Recently, large language models (LLMs) have emerged as promising tools for symbolic equation discovery, owing to their broad domain knowledge and strong reasoning capabilities. However, most existing LLM-based systems try to guess equations directly from data, without modeling the multi-step reasoning process that scientists often follow: first inferring physical properties such as symmetries, then using these as priors to restrict the space of candidate equations. We introduce KeplerAgent, an agentic framework that explicitly follows this scientific reasoning process. The agent coordinates physics-based tools to extract intermediate structure and uses these results to configure symbolic regression engines such as PySINDy and PySR, including their function libraries and structural constraints. Across a suite of physical equation benchmarks, KeplerAgent achieves substantially higher symbolic accuracy and greater robustness to noisy data than both LLM and traditional baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12259 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Think like a Scientist: Physics-guided LLM Agent for Equation Discovery Yang, Jianke Venkatachalam, Ohm Kianezhad, Mohammad Vadgama, Sharvaree Yu, Rose Artificial Intelligence Machine Learning Explaining observed phenomena through symbolic, interpretable formulas is a fundamental goal of science. Recently, large language models (LLMs) have emerged as promising tools for symbolic equation discovery, owing to their broad domain knowledge and strong reasoning capabilities. However, most existing LLM-based systems try to guess equations directly from data, without modeling the multi-step reasoning process that scientists often follow: first inferring physical properties such as symmetries, then using these as priors to restrict the space of candidate equations. We introduce KeplerAgent, an agentic framework that explicitly follows this scientific reasoning process. The agent coordinates physics-based tools to extract intermediate structure and uses these results to configure symbolic regression engines such as PySINDy and PySR, including their function libraries and structural constraints. Across a suite of physical equation benchmarks, KeplerAgent achieves substantially higher symbolic accuracy and greater robustness to noisy data than both LLM and traditional baselines. |
| title | Think like a Scientist: Physics-guided LLM Agent for Equation Discovery |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.12259 |