研究提出 Residual Agents 让 AI 科学家复现量子计算论文
Reimagining computational quantum research with AI scientists
这篇论文发现 AI 智能体很难复现量子论文的结果，然后靠记录修复经验把成功率从 68% 拉到 85%，成本只要 Claude Code 的三分之一，做科研自动化的可以看看思路。
arXiv 论文介绍 OmniQ 环境，将 59 篇量子科学论文转化为可执行复现任务，评估 5 个基于大模型的智能体系统和 6 个第三方 agent 框架。结果显示当前 AI 科学家大多无法复现已发表结果，论文内容与自主智能体所需信息存在错位。论文进一步提出 Residual Agents（RA），将经外部验证的修复流程沉淀为可复用经验。在固定基础模型下，RA 把 DeepSeek V4.1 Flash 的表现从 68% 提升到 85%，以 Claude Code with Opus 5 三分之一的成本达到同等水平。所有复现结果整合到基于 MCP 的可扩展平台上。
Reimagining computational quantum research with AI scientists
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.
