mlsanityData to 7 Oct 2026

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

arXiv 2610.10468 ↗First posted 7 Oct 2026cs.MA cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks also fits: Web, search, and research agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 24 of its 59 references that are in the map. First posted on arXiv 7 Oct 2026.

Builds on

24 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Towards a Science of Scaling Agent Systems9 Dec
  2. 2025Large Language Models Miss the Multi-Agent Mark27 May
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 21

  1. 2016Concrete Problems in AI Safetycited by 1,582
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  3. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  4. 2017Population Based Training of Neural Networkscited by 351
  5. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  6. 2024Frontier Models are Capable of In-context Schemingcited by 252
  7. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  8. 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)cited by 137
  9. 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 84
  10. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64
  11. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debatecited by 63
  12. 2024Algorithmic Collusion by Large Language Modelscited by 54
9 more
  1. 2025Demonstrating specification gaming in reasoning modelscited by 48
  2. 2024Cultural Evolution of Cooperation among LLM Agentscited by 30
  3. 2026Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphscited by 17
  4. 2025Magentic Marketplace: An Open-Source Environment for Studying Agentic Marketscited by 15
  5. 2025Exploring the use of AI authors and reviewers at Agents4Sciencecited by 13
  6. 2026From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Sciencecited by 7
  7. 2026AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Powercited by 3
  8. 2025Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agentscited by 1
  9. 2026CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Reviewcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
  2. 2026Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems
  3. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
  4. 2026Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
  5. 2026Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
  6. 2026MACC: Multi-Agent Collaborative Competition for Scientific Exploration
  7. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
  8. 2026Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies