Sirui Lu, a doctoral candidate at the Max Planck Institute for Quantum Optics, is developing TeXRA, an artificial intelligence framework that combines the inference capabilities of large-scale language models with computational tools to advance research in quantum physics. TeXRA has been applied to co-design quantum error-correcting codes using lateral diagonal gates with numerical search and to formal verification of tensor network theory within the Lean 4 Proof Assistant, going beyond just benchmarking LLM for coding tasks. This approach combines informal physical reasoning with rigorous numerical calculations and machine-checked proofs. Lu is also co-authoring Generative AI and Stochastic Thermodynamics: A Tale of Free Energies with Max Welling and Lars Holdijk, which will be published by Cambridge University Press, and focuses on the relationship between AI and fundamental physical principles.
TeXRA facilitates the collaborative design of quantum error-correcting codes featuring lateral diagonal gates through a multi-agent numerical search process, a technique that has traditionally relied on human expertise. This framework coordinates expert agents and builds both a research and verification system that bridges intuitive physical insights with rigorous numerical calculations and formal proofs. A forthcoming textbook will explain how concepts of stochastic thermodynamics influence the development of generative AI, while Lu’s research demonstrates the interconnectedness of applying AI to advance the understanding of quantum information and algorithms. He received his master’s degree from the Technical University of Munich and his bachelor’s degree from Tsinghua University.
He is co-author, with Max Welling and Lars Holdijk, of the forthcoming textbook Generative AI and Stochastic Thermodynamics: A Tale of Free Energys, to be published by Cambridge University Press.
Lu’s framework, named TeXRA, does more than simply leverage large language models for coding challenges. Coordinate professional agents to build both research and verification systems.
