AI自动生成高质量科研软件，能超越人类专家成果。
An AI system to help scientists write expert-level empirical software
- 用大模型+树搜索系统化优化代码质量，智能探索解决方案空间。
- 在生物信息学中发现40种新方法，性能超人类顶尖成果。
- 适合科研人员快速构建复杂计算工具，加速科学发现进程。
科学发现的循环常因手动编写计算实验软件而受阻。为此，我们提出经验研究助手（ERA），一个利用大语言模型（LLM）与树搜索（TS）的AI系统，旨在生成达到专家水平的科学软件，以最大化质量指标。该系统通过系统性改进质量指标并智能导航庞大解空间，实现对复杂研究思路的探索与整合。在生物信息学任务中，ERA发现了40种新型单细胞数据分析方法，其性能优于公开排行榜上的最优人工方法；在流行病学领域，生成的14个疫情预测模型超越了美国疾控中心（CDC）集成模型及所有其他单模型。此外，ERA还成功开发出用于地理空间分析、斑马鱼神经活动预测和积分数值求解的专家级软件，并设计出一种新颖的时间序列预测规则构造方法。通过在多样化任务中提出并实现创新解决方案，ERA显著推进了科学进步的速度。
原文摘要 · Abstract (English)
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we present Empirical Research Assistance (ERA), an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. The system uses a Large Language Model (LLM) and Tree Search (TS)\cite{silver2016mastering} to systematically improve the quality metric and intelligently navigate the large space of possible solutions. ERA achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a diverse range of tasks. In bioinformatics, ERA discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, ERA generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. ERA also produced expert-level software for geospatial analysis, neural activity prediction in zebrafish, and numerical solution of integrals, and a novel rule-based construction for time series forecasting. By devising and implementing novel solutions to diverse tasks, ERA represents a significant step towards accelerating scientific progress.
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。