发表机构
Transformer Lab（Transformer实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对共享计算池的数千研究智能体群体，提出基于六项原则、由制度明确组织的智能体社会，通过提案竞争分配资源，并在万级规模实验中实现约30%计算节省。
AI 中文摘要
研究智能体的部署正迈向由数千个共享同一计算池的智能体组成的群体，而当前大多数系统要么一次组织一个项目，要么让群体处于无组织状态。我们认为，这样的群体无论设计者是否提供组织，都会自发形成某种组织，因此设计者应明确提供组织，并且多智能体系统社区拥有实现这一目标的工具。我们提出一个智能体社会，即在明确制度下由持久智能体组成的群体，并将其发展为基于六项原则的研究者社会。首席研究员通过提案请求、独立评审和资助来竞争计算资源；人类管理者（市长）负责分配资源，但不指派任务。在一个由一万名研究者组成的运行中的社会中，仅被要求改进语言模型的预训练时，一个实验室报告了一种以约30%更少的计算量达到相同质量的方法，而测试该方法的实验室对此结果尚未达成一致。最后，我们为智能体社区提出六个开放问题。
英文摘要
Deployments of research agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave the population unorganized. We argue that such a population will acquire an organization whether or not its designers provide one, so designers should provide it explicitly, and that the multi-agent systems community holds the tools to do so. We propose a society of agents, a population of persistent agents under explicit institutions, and develop it for science as a society of researchers built on six principles. Principal investigators compete for compute through requests for proposals, independent review, and grants; a human governor, the mayor, allocates resources and assigns no tasks. In a running society of ten thousand researchers, asked only to improve the pretraining of language models, one lab reported a way to reach the same quality with about 30% less compute, a result the labs that tested it do not yet agree on. We close with six open problems for the agents community.
Comments4 pages. Short version of A Society of Researchers: Institutional Design for Populations of Autonomous Scientific Agents, doi:10.5281/zenodo.22922325
