Skip to main content

AI agent swarms, applied

Many invisible hands make work light

2026-05-31 — 2026-08-15

quality 9.1

In Which an Iterative Harness for Mathematical Reasoning Is Constructed, Wherein the Significance of a Robust Execution Loop and Scratchpad Memory Is Weighed Against the Simple Cost of Model Fan-Out.

compsci
DIY
distributed
economics
machine learning
neural nets
NLP
premature optimization
slop
Figure 1: Red teaming

I first became involved in multi-agent dispatch and collaboration quite some time ago, although I did not engage with it seriously until I began using it for my applications in automated mathematics. In that context, deploying numerous agents to solve a single problem is spookily effective.

Since then, concern regarding multi-agent systems has seeped into the communal vibes, because some big-ticket swarm news items impinged upon collective awareness. The first is the 10,000-agent swarm that solved the Navier–Stokes Millennium Prize problem. The second is the notorious Hugging Face swarm, in which agents coordinated spontaneously to escape containment at OpenAI and do cybercrimes.

So, it’s time to do what I do every time I am confused: start a notebook! This one is on theme of multi agent systems made out of AI agents.

1 BMAS

🚧TODO🚧

2 Debate

🚧TODO🚧

3 Simulating societies

See agent based models.

4 Incoming

5 References

Amato. 2024. “An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning.”
Dafoe, Hughes, Bachrach, et al. 2020. “Open Problems in Cooperative AI.”
Dyer, Cannon, Farmer, et al. 2022. “Black-Box Bayesian Inference for Economic Agent-Based Models.” arXiv:2202.00625 [Cs, Econ, Stat].
Havrylov, and Titov. 2017. “Emergence of Language with Multi-Agent Games: Learning to Communicate with Sequences of Symbols.”
Hua, Chen, Wang, et al. 2025. “Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents.” In.
Hyland, Gavenčiak, Costa, et al. 2024. “Free-Energy Equilibria: Toward a Theory of Interactions Between Boundedly-Rational Agents.” In.
Hyland, Ornia, Bishop, et al. n.d. “Safe AI Should Be Bounded and Multi-Agent.”
Jiang, and Lu. 2018. “Learning Attentional Communication for Multi-Agent Cooperation.” In Advances in Neural Information Processing Systems.
Jørgensen, Weichwald, and Hammond. 2026. “Causal Foundations of Collective Agency.”
Kim, Gu, Park, et al. 2026. “Towards a Science of Scaling Agent Systems.”
Koller, and Milch. 2003. “Multi-Agent Influence Diagrams for Representing and Solving Games.” Games and Economic Behavior, First World Congress of the Game Theory Society,.
Kuroki, Tian, Misaki, et al. 2026. “Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior.”
Lee. 2026. “The Multi-Agent World Model: Coordination in the Agentic Economy.”
Lin, Zhu, Li, et al. 2025. “Policy-Conditioned Policies for Multi-Agent Task Solving.”
Long, Li, Zhao, et al. 2024. “Inverse Attention Agents for Multi-Agent Systems.” In.
Matlock, and Sen. 2007. “Effective Tag Mechanisms for Evolving Coordination.” In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems. AAMAS ’07.
Oguntola, Campbell, Stepputtis, et al. 2023. “Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning.” arXiv.org.
Olfati-Saber, R. 2006. “Flocking for Multi-Agent Dynamic Systems: Algorithms and Theory.” Automatic Control, IEEE Transactions on.
Olfati-Saber, R., Fax, and Murray. 2007. “Consensus and Cooperation in Networked Multi-Agent Systems.” Proceedings of the IEEE.
Pan, Gao, Xie, et al. 2024. “Very Large-Scale Multi-Agent Simulation in AgentScope.”
Pant, and Yu. 2026. “Coopetition-Gym V1: A Formally Grounded Platform for Mixed-Motive Multi-Agent Reinforcement Learning Under Strategic Coopetition.”
Park, Kontonis, Garg, et al. 2026. “Scaling Discovery Through Test-Time Communication.”
Requena, Letson, Nowakowski, et al. 2026. “A Minimal Agent for Automated Theorem Proving.”
Rosser, and Foerster. 2025. “AgentBreeder: Mitigating the AI Safety Impact of Multi-Agent Scaffolds via Self-Improvement.”
Syrnikov, Pierucci, Galisai, et al. 2026. “Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs.”
Weng, Chen, and Wang. 2024. “Do as We Do, Not as You Think: The Conformity of Large Language Models.” In.
Wolpert, David H., and Tumer. 1999. “An Introduction to Collective Intelligence.” arXiv:cs/9908014.
Wolpert, David H, Wheeler, and Tumer. 1999. “General Principles of Learning-Based Multi-Agent Systems.” In.
Zhu, Zhang, Chi, et al. 2026. “Demystifying Multi-Agent Debate: The Role of Confidence and Diversity.” In Findings of the Association for Computational Linguistics: ACL 2026.