用虚拟实验室群自动发现高性能神经算子，靠智能体协作与竞争实现创新。
An Agentic AI Scientific Community for Automated Neural Operator Discovery
- 构建由智能体组成的虚拟科研社区，通过引用机制优胜劣汰。
- 在5个偏微分方程问题上发现高精度、低参数的混合神经算子架构。
- 需大模型智能体维持多样性，规则替代导致创新力退化。
我们提出一种基于人工智能科研共同体的自主神经算子发现方法，该共同体由一群虚拟实验室构成，这些实验室在基于引用影响力的经济机制下相互协作与竞争。高引用实验室会催生追随其研究方向的新实验室，并淘汰表现不佳者。每个虚拟实验室包含三个智能体：负责提出架构的大语言模型规划者、执行训练与评估的数值工作者，以及参与跨实验室同行评审的大语言模型评审者。所有实验室共享一组通用构建模块，包括DeepONet（分支-主干）、傅里叶、Transformer（注意力）、小波和残差卷积神经算子。我们在五个问题上进行评估：分段回归、一维线性输运与Burgers方程，以及二维纳维-斯托克斯与达西流方程，每项问题重复模拟三次。结果表明，该人工智能科研共同体能够发现高精度、低参数的神经算子架构。全部9623次大模型调用均被记录与审计，显示规划者在99.8%的决策中选择混合多种家族架构，持续生成多家族混合结构。通过将实验室中的大模型替换为规则基替代方案的消融实验表明，系统在多个案例中退化为单一家族堆叠，证明大模型智能体对维持多样性至关重要。结果暗示神经算子不存在普适最优解，即‘无免费午餐’定理。代码、配置及完整大模型对话记录已公开于https://github.com/luislootx/AI-SC。
原文摘要 · Abstract (English)
We present an agentic approach to autonomous neural operator discovery based on an AI scientific community, which consists of a swarm of virtual laboratories that interact under a citation-based economy of influence. Highly-cited labs found new labs that follow their research direction and replace non-performing labs. Each virtual lab contains three agents: an LLM planner that proposes an architecture, a numerical worker that trains and measures it, and an LLM reviewer that participates in cross-lab peer review. All labs share a common vocabulary consisting of DeepONet (branch-trunk), Fourier, Transformer (attention), wavelet, and residual convolutional neural operator building blocks. We evaluate the neural operator AI scientific community on five problems, namely piecewise regression, the linear advection and Burgers 1D PDEs, and the Navier-Stokes and Darcy flow 2D PDEs, while repeating the simulation three times for each problem. The results show that the neural operator AI scientific community is capable of discovering high-accuracy, low-parameter-count neural operator architectures. All 9,623 LLM calls are logged and audited, which reveals that the virtual lab LLM planners choose to hybridize in 99.8% of their logged decisions, consistently returning multi-family hybrids. Moreover, we conducted an ablation study by replacing the LLM agents in each lab by rule-based alternatives, which caused the scientific community to collapse to non-hybridized single-family stacks in several cases, showing that LLM agency is needed to preserve diversity. The results suggest a no-free-lunch theorem for neural operators: there is no universal winner. The code, configurations, and the complete LLM transcripts are released at https://github.com/luislootx/AI-SC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。