Aster：比现有方法快20倍的自主科学发现
Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods
AI总结：
Aster是一种能快速自主发现科学问题的AI代理，通过减少迭代次数提升效率，适用于长评估时间的任务，如机器学习训练，并在多个领域取得SOTA成果。
摘要：
我们介绍了Aster，一种能够自主进行科学发现的AI代理，其运行速度比现有框架快超过20倍。给定一个任务、一个初始程序和一个评估程序性能的脚本，Aster会迭代改进程序，通常导致新的最先进性能。Aster显著减少发现新方法所需的迭代次数，将可处理的问题领域扩展到包括长评估时间的任务，如多小时的机器学习训练运行。我们应用Aster到数学、GPU内核工程、生物学、神经科学和语言模型训练问题上。具体包括：Erdos最小重叠问题、优化TriMul内核、单细胞分析去噪问题、训练神经活动预测模型以在ZAPBench上表现良好，以及NanoGPT速度竞赛。Aster在每个任务中均取得SOTA结果，除了ZAPBench，其性能与最佳人类解决方案相匹配，但计算量仅为1/190。Aster可通过asterlab.ai的网页界面和API访问。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
