paper-with-me

홈 › Papers

Agentic Exploration of Physics Models

2025-09-29 · Maximilian Nägele, Florian Marquardt 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.

📄 PDF Abstract BibTeX arXiv:2509.24978

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research

2026-04-16 · Tingjia Miao, Wenkai Jin, Muhua Zhang, Jinxin Tan 외 arxiv

The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension…

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

2026-03-03 · Siwei Zhang, Yun Xiong, Xi Chen, Zi'an Jia 외 arxiv

Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning.…

Reinforcement Learning

Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations

2026-02-26 · Abhijeet Vishwasrao, Francisco Giral, Mahmoud Golestanian, Federica Tonti 외 arxiv

Flow physics and more broadly physical phenomena governed by partial differential equations (PDEs), are inherently continuous, high-dimensional and often chaotic in nature. Traditionally, researchers have explored these …

Drug Discovery

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean

2026-04-24 · Jordan Meadows, Lan Zhang, Andre Freitas arxiv

Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit{e.g.} Dirac notatio…

Mathematical ReasoningCode Generation

PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research

2025-12-22 · Tingjia Miao, Jiawen Dai, Jingkun Liu, Jinxin Tan 외 arxiv

Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires deep domain expertise, long-horizon reasoning, and rel…