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

TL;DR

PhysMaster is an autonomous AI physicist that integrates abstract reasoning, numerical computation, and a layered knowledge base to accelerate, automate, and enable discovery in complex physics research.

Contribution

It introduces PhysMaster, an LLM-based agent combining reasoning, computation, and a layered data universe for end-to-end physics research automation.

Findings

Accelerates research from months to hours.

Autonomously executes hypothesis-driven research loops.

Explores open problems independently.

Abstract

Advances in LLMs have produced agents with knowledge and operational capabilities comparable to human scientists, suggesting potential to assist, accelerate, and automate research. However, existing studies mainly evaluate such systems on well-defined benchmarks or general tasks like literature retrieval, limiting their end-to-end problem-solving ability in open scientific scenarios. This is particularly true in physics, which is abstract, mathematically intensive, and requires integrating analytical reasoning with code-based computation. To address this, we propose PhysMaster, an LLM-based agent functioning as an autonomous theoretical and computational physicist. PhysMaster couples absract reasoning with numerical computation and leverages LANDAU, the Layered Academic Data Universe, which preserves retrieved literature, curated prior knowledge, and validated methodological traces, enhancing decision reliability and stability. It also employs an adaptive exploration strategy balancing efficiency and open-ended exploration, enabling robust performance in ultra-long-horizon tasks. We evaluate PhysMaster on problems from high-energy theory, condensed matter theory to astrophysics, including: (i) acceleration, compressing labor-intensive research from months to hours; (ii) automation, autonomously executing hypothesis-driven loops ; and (iii) autonomous discovery, independently exploring open problems.