ScholarPulse 日报 2026-10-19

2026-10-19 学术简报：2 篇。该研究证实大语言模型智能体能够自动化执行科学研究的复现与稳健性分析，有效辅助专家进行同行评审。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery	arXiv	2026-10-16	AI-Agent	高
2	Leveraging verifiable structure in quantum circuits to find more efficient compilations with agentic AI	arXiv	2026-10-16	RAG	高

重点论文与技术动态

1. AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery

来源：arXiv
日期：2026-10-16
作者/机构：Shicheng Liu, Krista Opsahl-Ong, Andrew Drozdov, Julian Killingback, Arnav Singhvi, Ronak Pradeep
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.AI, cs.CL

一句话结论

该研究证实大语言模型智能体能够自动化执行科学研究的复现与稳健性分析，有效辅助专家进行同行评审。

核心内容

构建了包含 20 篇已发表医学论文及其复现所需资源的基准数据集 SEER-Repro。
开发的 AI 智能体成功复现了 2,190 个原子断言中的 77.4%，并提供了可执行基准。
稳健性分析流程在 9.5% 完全复现的发现中检测到可能影响最终结论的分析选择，并标记供专家复审。

方法与数据

数据：基于美国 SEER 癌症登记数据库构建的 20 篇已发表论文基准数据 SEER-Repro。
方法：利用 LLM 智能体自动化复现断言，通过识别分析选择、提出合理的替代方案并重新运行分析来检验结论稳健性。

价值判断

值得关注：证明了 AI 可系统化降低人工复现成本，并将专家精力精准引导至可能影响研究结论的关键分析选择上。
可复用点：SEER-Repro 基准数据集，以及提出替代分析方案并重新运行验证的智能体分析流程。
局限/待核查：AI 仍有 22.6% 的断言未能成功复现；标记出的关键分析选择最终仍需专家人工复核。

摘要

Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We investigate whether LLM agents can help automate reproduction and robustness analysis, using a medical case study grounded in the Surveillance, Epidemiology, and End Results (SEER) database, a widely used U.S. cancer registry underlying tens of thousands of published studies. First, we introduce SEER-Repro, a benchmark of 20 published SEER-based papers together with the data and resources required to reproduce their findings. Second, we create an AI agent that successfully reproduces 77.4% of 2,190 atomic claims, while providing executable baselines for further analysis. Third, we develop an agentic analysis pipeline to test the robustness of the medical findings by identifying analytical choices underlying each finding, proposing defensible alternatives, and rerunning the analysis to determine whether those choices affect the conclusion. Across published papers in SEER-Repro, our pipeline identifies potentially consequential analytical choices in 9.5% of fully reproduced findings and flags them for expert review. These results show how LLM agents can support scientific review by reproducing findings, systematically testing their robustness, and directing expert attention toward potentially consequential analytical choices.

2. Leveraging verifiable structure in quantum circuits to find more efficient compilations with agentic AI

来源：arXiv
日期：2026-10-16
作者/机构：Tanuj Khattar, Nicholas C. Rubin, Craig Gidney, Michael Broughton, Guang Hao Low, Ryan Babbush
主题标签：RAG, arXiv
推荐等级：高
分类：quant-ph

一句话结论

本文提出利用 AI 智能体优化量子线路编译的新范式，通过将瓶颈子程序约束为经典可验证结构来实现高效合成与验证。

核心内容

当关键子程序仅由可逆经典逻辑、定相操作和基于测量的反计算组成时，可通过经典输入高效模拟与模糊测试来认证近似电路合成。
覆盖三大应用瓶颈：惯性约束聚变模拟中的 $1/\sqrt{x}$ 计算、量子干涉中的里德-所罗门码解码，以及化学模拟中的量子查找表与吉文斯旋转。
探讨了算法的参考实现与验证约束，旨在发起 Kaggle 竞赛以加速 AI 在量子编译优化上的研究。

方法与数据

采用基于可验证经典结构模拟的模糊测试进行认证；具体评测数据集摘要未明确，仅提及提供了算法参考实现。

价值判断

值得关注：开辟了结合 AI 智能体与量子编译优化的有效路径，并借助 Kaggle 竞赛促进跨学科研究。
可复用点：针对受限量子结构利用模糊测试快速认证近似合成的方法范式。
局限/待核查：认证有效性依赖输入分布的合理假设，且仅适用于特定结构子程序；实际优化幅度有待竞赛成果验证。

摘要

We discuss an effective paradigm of utilizing AI agents to better compile quantum circuits when one can constrain bottleneck subroutines to have some form of classically verifiable structure. For example, when critical subroutines are composed exclusively of reversible classical logic, phasing operations, and measurement based uncomputation, one can efficiently simulate execution for classical inputs. This property facilitates efficient certification of approximate circuit synthesis via a form of fuzz testing, provided suitable assumptions on the input distribution. While this pattern was recently exploited to improve quantum cryptanalysis circuits, here we highlight the flexibility of the broader approach by discussing three important applications. (1) The computation of $1/\sqrt{x}$ that bottlenecks real space simulations of the Coulomb operator such as those important for modeling inertial confinement fusion reactors. (2) The decoding of Reed-Solomon codes which bottlenecks the decoded quantum interferometry algorithm when used to approximately solve the optimal polynomial intersection problem. And (3) the quantum look-up tables and controlled application of Givens rotations that bottleneck the most performant quantum algorithms for simulating chemistry in second quantization. We discuss reference implementations of these algorithms and how they can be constrained and verified in the interest of seeding a Kaggle competition designed to accelerate AI-based research into the optimization of their compilation.