迈向科学外皮层
Towards a Science Exocortex
AI总结：
本文针对AI对科学研究的潜在价值，综述智能体AI系统进展，提出构建由AI智能体集群组成的科学外皮层，以扩展研究人员的认知与意志。
摘要：
人工智能（AI）方法有望彻底革新智力工作，生成式AI可实现文本分析、文本生成以及简单决策或推理的自动化。其对科学的影响才刚刚开始，但机遇十分重大，因为科学研究从根本上依赖于长链条的认知工作。本文综述了智能体AI系统的最新进展，并探讨了如何拓展这些方法以对科学产生更大影响。我们提出开发外皮层（exocortex）——一种人类认知的合成扩展装置。科学外皮层可被设计为一个AI智能体集群，每个智能体各自简化研究人员的特定任务，而它们之间的相互通信会产生涌现行为，极大地扩展研究人员的认知与意志。
英文摘要：
Artificial intelligence (AI) methods are poised to revolutionize intellectual work, with generative AI enabling automation of text analysis, text generation, and simple decision making or reasoning. The impact to science is only just beginning, but the opportunity is significant since scientific research relies fundamentally on extended chains of cognitive work. Here, we review the state of the art in agentic AI systems, and discuss how these methods could be extended to have even greater impact on science. We propose the development of an exocortex, a synthetic extension of a person's cognition. A science exocortex could be designed as a swarm of AI agents, with each agent individually streamlining specific researcher tasks, and whose inter-communication leads to emergent behavior that greatly extend the researcher's cognition and volition.
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。
