Reimagining computational quantum research with AI scientists

📄 arXiv: 2611.02833v1 📥 PDF

作者: Yuxuan Du, Hanqing Zhao, Xinbiao Wang, Yiming Lu, Kaining Zhang, Dacheng Tao

分类: quant-ph, cs.AI, cs.LG

发布日期: 2026-11-02

备注: 57 pages, 19 figures. Comments are welcome


💡 一句话要点

提出OmniQ与RA以解决量子计算研究中的自动化挑战

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 量子计算 自动化研究 AI科学家 重现任务 自我改进 虚拟研究环境 工作流修复

📋 核心要点

  1. 当前AI科学家在重现已发表的量子计算研究结果时存在显著失败,揭示了科学论文与自主代理需求之间的信息不匹配。
  2. 提出OmniQ虚拟研究环境,将已发表研究转化为可执行任务,并开发Residual Agents(RA)以改进AI科学家的自主学习能力。
  3. RA在DeepSeek V4.1 Flash性能上从68%提升至85%,在成本上仅为Claude Code与Opus 5的三分之一,展现出显著的性能提升。

📝 摘要(中文)

AI科学家正在推动各科学领域的自动化研究,但将科学记录转化为自主发现的基础仍然困难重重。本文揭示了这一转变的根本障碍,并展示了在计算量子科学中克服这一障碍的途径。我们引入OmniQ,一个经过专家审核的虚拟研究环境,将已发表的研究转化为可执行的重现任务。通过对59篇论文的系统评估,我们发现当前的AI科学家在重现已发表结果时常常失败,揭示了科学论文传达的信息与自主代理所需的信息之间的根本不匹配。相较之下,人类专家的干预能够将这些失败转化为成功的重现,表明缺失的信息可以被识别并转化为可重用的研究经验。基于此观察,我们开发了Residual Agents(RA),一种量子定制的自我改进AI科学家,能够将外部验证的工作流修复提炼为研究经验。RA在固定基础模型和有限适应预算下显著提升了研究性能。

🔬 方法详解

问题定义:本文旨在解决AI科学家在量子计算研究中无法有效重现已发表结果的问题,现有方法面临信息传达不匹配的挑战。

核心思路:通过引入OmniQ虚拟研究环境,将科学论文转化为可执行的重现任务,并利用人类专家的干预来识别缺失信息,进而开发出Residual Agents(RA)以实现自我改进。

技术框架:整体架构包括OmniQ环境、AI科学家代理系统和RA模块。OmniQ负责任务转化,AI科学家执行重现任务,RA则通过学习外部验证的工作流修复来提升自身能力。

关键创新:RA的核心创新在于其自我改进能力,通过提炼专家修复经验来增强AI科学家的重现能力,这一机制与传统的静态学习方法有本质区别。

关键设计:RA的设计包括对外部验证工作流的提炼过程,采用适应性学习策略和优化的损失函数,以确保在固定基础模型下的性能提升。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,RA在DeepSeek V4.1 Flash性能上从68%提升至85%,与Claude Code和Opus 5的性能相当,但成本仅为其三分之一,展现了显著的性能提升和经济效益。

🎯 应用场景

该研究的潜在应用领域包括量子计算、材料科学和复杂系统模拟等,能够为科学研究的自动化提供新的思路和工具,推动科学发现的效率和准确性。未来,随着AI科学家技术的不断进步,可能会在更多科学领域实现自主发现和创新。

📄 摘要(原文)

AI scientists are expanding automated research across scientific domains, yet their ability to turn the scientific record into a foundation for autonomous discovery remains elusive. Here we uncover a fundamental barrier to this transition and demonstrate a route to overcome it in computational quantum science, where advances shape both what we can learn from complex quantum systems and what quantum computing can ultimately deliver. To identify this barrier, we introduce OmniQ, an expert-audited virtual research environment that converts published studies into executable reproduction tasks. Across 59 papers spanning classical simulation, quantum algorithms and quantum-property characterization, we systematically evaluate five agentic systems powered by large language models and six third-party agent harnesses. Our findings reveal that current AI scientists often fail to reproduce published results, exposing a fundamental mismatch between what scientific papers communicate and what autonomous agents require. By contrast, human expert intervention can turn these failures into successful reproductions, showing that the missing information can be identified and converted into reusable research experience. Guided by this observation, we develop Residual Agents (RA), a quantum-tailored self-improving AI scientist that distils externally verified workflow repairs into such experience. RA substantially improves research performance under fixed base models and limited adaptation budgets. For example, RA raises DeepSeek V4.1 Flash performance from 68% to 85%, matching Claude Code with Opus 5 at a third of its cost despite using a weaker base model. We integrate all reproduced results into an extensible platform built on the model context protocol, making verified research workflows directly accessible to AI scientists and allowing new scientific papers to be continuously incorporated.