Aster：实现比现有方法快20倍以上的自主科学发现

摘要

我们推出Aster——一款用于自主科学发现的人工智能代理，其运行速度可达现有框架的20倍以上。给定任务、初始程序及性能评估脚本后，Aster能持续迭代优化程序，往往能实现新的最先进性能。该框架将新发现所需迭代次数显著减少，使得可处理问题领域扩展至包含长评估周期的任务（例如耗时数小时的机器学习训练）。我们将Aster应用于数学、GPU内核工程、生物学、神经科学及语言模型训练等领域。具体包括：埃尔德什最小重叠问题、TriMul内核优化、单细胞分析去噪问题、训练神经活动预测模型以在ZAPBench上取得优异表现，以及NanoGPT速通竞赛。除ZAPBench任务中仅用不到1/190的计算量即达到最佳人工解决方案水平外，Aster在其他所有任务中均实现了最先进成果。用户可通过asterlab.ai的网页界面与API访问Aster平台。

English

We introduce Aster, an AI agent for autonomous scientific discovery capable of operating over 20 times faster than existing frameworks. Given a task, an initial program, and a script to evaluate the performance of the program, Aster iteratively improves the program, often leading to new state-of-the-art performances. Aster's significant reduction in the number of iterations required for novel discovery expands the domain of tractable problems to include tasks with long evaluation durations, such as multi-hour machine learning training runs. We applied Aster to problems in mathematics, GPU kernel engineering, biology, neuroscience, and language model training. More specifically: the Erdos minimum overlap problem, optimizing the TriMul kernel, a single-cell analysis denoising problem, training a neural activity prediction model to perform well on ZAPBench, and the NanoGPT Speedrun Competition. Aster attains SOTA results in every task, except for ZAPBench, where it matches the performance of the best human solution with less than 1/190th of the compute. Aster is accessible via a web interface and API at asterlab.ai.

Aster：实现比现有方法快20倍以上的自主科学发现

Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods

摘要

Support