OmniQEC: Discovering Practical Quantum Error-Correcting Codes by an AI Scientist

Quantum error correction (QEC) is indispensable for scalable fault-tolerant quantum computing, but discovering effective QEC codes is challenging due to the interplay between code structure, hardware, syndrome extraction, and decoding. OmniQEC formulates QEC design as an iterative discovery process where an LLM-based orchestrator coordinates code generation, code-level screening, syndrome-extraction synthesis, and decoder-based circuit evaluation. Its core combines a self-evolving reasoning mechanism with a slow–fast synergistic workflow: a fast loop explores candidates using inexpensive code-level proxies, while a slow loop performs physically grounded circuit-level evaluation and feeds evidence back into the search. Evaluated across four qLDPC construction families, three LLM backends, and 14 total-physical-qubit budgets per backend, the discovered codes show steadily improving logical-error suppression with increasing physical-qubit budgets and outperform BB codes with [[72,12,6]] and [[144,12,12]] under complete-implementation budgets of 98 and 240 physical qubits, respectively. These findings pave the way towards LLM-assisted QEC discovery grounded in physically informed code–circuit–decoder co-design.