---
title: "OmniQEC: Discovering Practical Quantum Error-Correcting Codes by an AI Scientist"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.25865v1"
permalink: "https://feed.astralor.com/items/itm_c9f9a56e1047279987fc3877"
published: "2026-07-28T15:31:26.000Z"
score: 78
channel: "tech"
tags: ["AI Scientists","OmniQEC","qLDPC codes","Large Language Models","Quantum Error Correction"]
---

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

## AI commentary

> This paper demonstrates the immense potential of LLMs in scientific discovery—especially for quantum computing researchers. OmniQEC offers a new paradigm for automatically exploring quantum error-correcting codes, going beyond theory to provide concrete hardware-friendly code examples and performance comparisons. Engineers working on quantum hardware and error correction will find it particularly valuable.

## At a glance

OmniQEC is an AI scientist system driven by large language models, designed to discover quantum error-correcting codes suitable for modern quantum processors. It formulates QEC design as an iterative process where an LLM-based orchestrator coordinates code generation, screening, syndrome extraction, and decoder-based circuit evaluation, employing a self-evolving reasoning mechanism with a slow-fast dual-loop workflow. Evaluated across four qLDPC code families and three LLM backends, the discovered codes consistently show better logical-error suppression as physical-qubit budgets increase, outperforming BB codes under practical implementations, and are hardware-friendly for practical QEC deployment.

## Key points

- OmniQEC uses large language models as orchestrators to automatically discover quantum error-correcting codes.
- The system employs a slow-fast dual-loop workflow: a fast loop uses cheap proxies for screening, and a slow loop performs circuit-level evaluation with feedback.
- Under budgets of 98 and 240 physical qubits, the discovered codes outperform [[72,12,6]] and [[144,12,12]] BB codes respectively.
- The discovered codes are hardware-friendly and ready for deployment on modern quantum processors.

## Full text

Quantum error correction (QEC) is indispensable for scalable fault-tolerant quantum computing. However, discovering QEC codes that remain effective is challenging, as logical performance depends on the interplay between code structure, hardware, syndrome extraction, and decoding, which often impose competing requirements. Here we introduce OmniQEC, an efficient AI scientist for discovering QEC codes suited to deployment on modern quantum processors. OmniQEC formulates QEC design as an iterative discovery process in which an orchestrator, implemented by advanced large language models (LLMs), coordinates code generation, code-level screening, syndrome-extraction synthesis, and decoder-based circuit evaluation. At its core, OmniQEC combines a self-evolving reasoning mechanism with a slow--fast synergistic workflow: a fast loop explores candidates using inexpensive code-level proxies, whereas a slow loop performs physically grounded circuit-level evaluation and feeds the resulting evidence back into the search. We evaluate OmniQEC 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 the BB codes with $[\![72,12,6]\!]$ and $[\![144,12,12]\!]$ under complete-implementation budgets of 98 and 240 physical qubits, respectively. The discovered codes are hardware-friendly and may be of independent interest for practical QEC implementation. These findings pave the way towards LLM-assisted QEC discovery grounded in physically informed code--circuit--decoder co-design.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_c9f9a56e1047279987fc3877