A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents

Key points

• 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.1
• 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.1
• 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.1
• We close with six open problems for the agents community.1

Sources (1)

• [1]A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:30 PM

  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.

  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.

Extractive summary: sentences quoted from the sources.