# Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

arXiv: https://arxiv.org/abs/2609.01552 · HTML: https://mlsanity.com/paper/2609.01552/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Contemporary Symbolic Regression Methods and their Relative Performance](https://mlsanity.com/paper/2107.14351/) (2021)
- [End-to-end symbolic regression with transformers](https://mlsanity.com/paper/2204.10532/) (2022)
- [Neural Symbolic Regression that Scales](https://mlsanity.com/paper/2106.06427/) (2021)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [SymbolicGPT: A Generative Transformer Model for Symbolic Regression](https://mlsanity.com/paper/2106.14131/) (2021)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models](https://mlsanity.com/paper/2504.10415/) (2025)
- [Measuring memorization in language models via probabilistic extraction](https://mlsanity.com/paper/2410.19482/) (2024)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [SR-Scientist: Scientific Equation Discovery With Agentic AI](https://mlsanity.com/paper/2510.11661/) (2025)
- [PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors](https://mlsanity.com/paper/2507.15550/) (2025)
- [Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents](https://mlsanity.com/paper/2501.18411/) (2025)
- [Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab](https://mlsanity.com/paper/2507.02083/) (2025)
- [Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints](https://mlsanity.com/paper/2604.15664/) (2026)

## Built on by (most cited first, 2 of 2)

- [MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws?](https://mlsanity.com/paper/2609.35515/) (2026)
- [DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?](https://mlsanity.com/paper/2609.33357/) (2026)

## Abstract (arXiv)

Scientific law discovery has long been central to scientific progress, proceeding through iterative cycles of generating hypotheses, testing them against empirical evidence, and refining them under scientific constraints. As large language models (LLMs) become increasingly involved in scientific research, whether they can discover scientific laws and how to evaluate this ability remain open questions. A central evaluation challenge is to move beyond familiar published equations while keeping discovery tasks grounded in scientific data and constraints. We introduce SciLaws-Bench, a curated collection of scientific task packages grounded in the source literature, each linking a scientific problem, supporting data, published reference equations, and scientific-validity rubrics. Through agent-assisted curation and human verification, we assemble 118 problems spanning six disciplines, drawing on 381 papers, 291 candidate laws, and roughly 8M data points. Each problem supports two complementary evaluation settings. SciLaws-Real uses fixed scientific data to evaluate proposed laws for held-out predictive fit and scientific validity. SciLaws-Parallel evaluates recovery of a newly synthesized structural variant of a published equation through active queries to a simulator calibrated to the source data. Our evaluation reveals three limitations: good predictive fit need not imply scientific validity, recovering a published formula does not establish recovery of its new structural terms, and candidate selection remains a bottleneck in scientific law discovery. Project page: https://yiyihum.github.io/SciLaws-Bench