Building an Autonomous AI Physicist

by Tingjia Miao (Shanghai Jiao Tong University)

Friday 6 Feb 2026, 10:30 → 11:30 Asia/Shanghai

S408

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.

Biography:
Tingjia Miao received B.S. in Physics with honor at Zhiyuan College, Shanghai Jiao Tong University, and is a Ph.D. student at the School of Artificial Intelligence, Shanghai Jiao Tong University, under the supervision of Associate Professor Siheng Chen. His research focuses on AI Agents and AI for Science. From 2023 to 2024, he served as a Research Assistant at the Tsung-Dao Lee Institute, Shanghai Jiao Tong University, working on theoretical condensed matter physics and supervised by Prof. Wei Ku. He have conducted research internships at ByteDance Seed and the School of Computer Science, Peking University. Since 2025, he has been collaborating with DP Technology, contributing substantially to the development of the SciMaster scientific agent ecosystem.