From Paper to Program: A Multi-Stage LLM-Assisted Workflow for Accelerating Quantum Many-Body Algorithm Development
This accelerates computational physics research by providing a reproducible paradigm for quantum algorithm development, though it is incremental as it builds on existing LLM and tensor network methods.
The authors tackled the problem of translating quantum many-body theory into scalable software by developing a multi-stage LLM-assisted workflow that generates exact, matrix-free operations, achieving a 100% success rate across 16 model combinations and compressing development from months to under 24 hours.
Translating quantum many-body theory into scalable software traditionally requires months of effort. Zero-shot generation of tensor network algorithms by Large Language Models (LLMs) frequently fails due to spatial reasoning errors and memory bottlenecks. We resolve this using a multi-stage workflow that mimics a physics research group. By generating a mathematically rigorous LaTeX specification as an intermediate blueprint, we constrain the coding LLM to produce exact, matrix-free $\mathcal{O}(D^3)$ operations. We validate this approach by generating a Density-Matrix Renormalization Group (DMRG) engine that accurately captures the critical entanglement scaling of the Spin-$1/2$ Heisenberg model and the symmetry-protected topological (SPT) order of the Spin-$1$ AKLT model. Testing across 16 combinations of leading foundation models yielded a 100\% success rate. By compressing a months-long development cycle into under 24 hours ($\sim 14$ active hours), this framework offers a highly reproducible paradigm for accelerating computational physics research.