QuantumNovelty：用于量子论文与专利的评审式审查及可专利性筛选的技能编排语言智能体

中文摘要 AI 辅助

语言模型智能体越来越多地产出量子科学相关成果；本文探究同样的智能体范式是否也能以可审计、可复现且成本透明的形式对这些成果进行审查。我们提出QuantumNovelty，这是一款开源的技能编排语言智能体，既可以生成量子计算相关产物（论文、帕累托前沿 ansatz 候选方案及专利草稿），也能通过模拟的评审专家及专利审查员小组对这些产物进行审查。其设计贡献在于构建了一个审计与证伪层，该层由确定性门构成，包括严格帕累托支配、基于磁盘产物的数值重计算、Wilson 小样本区间以及跨供应商共识防护机制，用于约束而非生成允许留存的主张；每一次模型调用都会记录后端、 token 数量及成本。我们不宣称其准确率优于人类专家，仅验证无需人类标签即可核查的内容：在植入式对抗语料库上，确定性门捕获了所有植入式过度主张且无假阳性；在首次部署（6篇手稿及1项已授权专利，实测成本约24美元）中，审查小组在单侧样本上的方向比公开接受记录更为保守。该框架属于决策支持工具，而非同行评审或专利审查的替代方案，我们完整报告了其机制在真实输入上未被运用的情况。

英文摘要

Language-model agents increasingly produce quantum-science results; we ask whether the same agentic paradigm can also scrutinize them in an auditable, reproducible, and cost-transparent form. We present QuantumNovelty, an open-source skill-orchestrating language agent that both generates quantum-computing artifacts (papers, Pareto-front ansatz candidates, and patent drafts) and reviews them through simulated referee and patent-examiner panels. Its design contribution is an audit-and-falsify layer of deterministic gates -- strict Pareto domination, numerical recomputation from on-disk artifacts, Wilson small-sample intervals, and a cross-vendor consensus guard -- that constrains, rather than generates, the claims allowed to survive; every model call is logged with backend, token count, and cost. We make no accuracy claim against human experts, and validate only what is checkable without human labels: on a planted adversarial corpus the deterministic gates catch every planted overclaim with no false positives, and on a first deployment (six manuscripts and one granted patent, at a measured cost of about twenty-four US dollars) the panels are directionally more conservative than the public acceptance record, on a one-sided sample. The framework is decision support, not a replacement for peer review or patent examination, and we report in full where its mechanisms remain unexercised on real inputs.

发表机构

• Johns Hopkins University（约翰斯·霍普金斯大学）

机构由 AI 辅助整理，请以论文原文为准。