# Agentic Exploration of Physics Models

arXiv: https://arxiv.org/abs/2509.24978 · HTML: https://mlsanity.com/paper/2509.24978/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 32)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Discovering Symbolic Models from Deep Learning with Inductive Biases](https://mlsanity.com/paper/2006.11287/) (2020)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models](https://mlsanity.com/paper/2504.16074/) (2025)
- [PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning](https://mlsanity.com/paper/2502.12054/) (2025)
- [CRISPR-GPT for Agentic Automation of Gene-editing Experiments](https://mlsanity.com/paper/2404.18021/) (2024)
- [BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments](https://mlsanity.com/paper/2405.17631/) (2024)
- [Active learning machine learns to create new quantum experiments](https://mlsanity.com/paper/1706.00868/) (2017)
- [AstroLLaMA: Towards Specialized Foundation Models in Astronomy](https://mlsanity.com/paper/2309.06126/) (2023)
- [DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation](https://mlsanity.com/paper/2507.14267/) (2025)
- [Agents for self-driving laboratories applied to quantum computing](https://mlsanity.com/paper/2412.07978/) (2024)
- [Quantum Many-Body Physics Calculations with Large Language Models](https://mlsanity.com/paper/2403.03154/) (2024)
- [Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models](https://mlsanity.com/paper/2501.05382/) (2025)
- [Can Theoretical Physics Research Benefit from Language Agents?](https://mlsanity.com/paper/2506.06214/) (2025)
- [An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design](https://mlsanity.com/paper/2506.06935/) (2025)
- [Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery](https://mlsanity.com/paper/2507.07257/) (2025)
- [AI Agents for Photonic Integrated Circuit Design Automation](https://mlsanity.com/paper/2508.14123/) (2025)
- [TopoMAS: Large Language Model Driven Topological Materials Multiagent System](https://mlsanity.com/paper/2507.04053/) (2025)

## Built on by (most cited first, 6 of 6)

- [Towards autonomous quantum physics research using LLM agents with access to intelligent tools](https://mlsanity.com/paper/2511.11752/) (2025)
- [MaD Physics: Evaluating information seeking under constraints in physical environments](https://mlsanity.com/paper/2605.10820/) (2026)
- [Discovering physical mechanisms from experiment-simulation mismatches](https://mlsanity.com/paper/2604.26703/) (2026)
- [ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation](https://mlsanity.com/paper/2608.10792/) (2026)
- [Adaptive Entangled Game Modules in Artificial General Intelligence](https://mlsanity.com/paper/2609.09226/) (2026)
- [How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes](https://mlsanity.com/paper/2610.00435/) (2026)

## Abstract (arXiv)

The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open challenge to fully automate the heuristic, iterative loop required to discover the laws of an unknown system by exploring it through experiments and analysis, without tailoring the approach to the specifics of a given task. Here, we introduce SciExplorer, an agent that leverages large language model tool-use capabilities to enable exploration of systems without any domain-specific blueprints, and apply it to physical systems that are initially unknown to the agent. We test SciExplorer on a broad set of models spanning mechanical dynamical systems, wave evolution, and quantum many-body physics. Despite using a minimal set of tools, primarily based on code execution, we observe impressive performance on tasks such as recovering equations of motion from observed dynamics and inferring Hamiltonians from expectation values. The demonstrated effectiveness of this setup opens the door toward similar scientific exploration in other domains, without the need for fine-tuning or task-specific instructions.