研究者社会：为自主研究智能体群体设计制度
原标题：A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
AI 摘要
论文提出将大规模自主研究智能体群体组织为「研究者社会」，以明确的制度（角色、算力分配、评审、声誉、共享记忆）来管理数千个共享算力的持久智能体。作者以科学制度为蓝本，让首席研究员通过提案申请、独立评审和资助竞争算力，人类「市长」只分配资源而不指派任务。在一个一万名研究者组成的社会中，仅被要求改进语言模型预训练，某实验室报告称可用约减少30%的算力达到同等质量，但测试该结果的实验室尚未达成一致。文章最后提出智能体社区的六个开放问题。
正文节选
A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents Abstract. 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