cs.MAOct 23, 2024

The Hive Mind is a Single Reinforcement Learning Agent

Authors: Karthik Soma, Yann Bouteiller, Heiko Hamann, Giovanni Beltrame

Organizations: MIST Lab, Department of Computer and Software Engineering, Polytechnique Montréal, Montréal, . · Mila - Quebec AI Institute . · Department of Computer and Information Science, University of Konstanz, Konstanz, Germany .

Abstract

Decision-making is an essential attribute of any intelligent agent or group. Natural systems are known to converge to effective strategies through at least two distinct mechanisms: collective decision-making via imitation of others, and trial-and-error by a single agent. This paper establishes an equivalence between these two paradigms. We show that the emergent distributed cognition (sometimes referred to as the hive mind) arising from individuals following simple, local imitation-based rules is that of a single online reinforcement learning (RL) agent aggregating action-value samples from many parallel instances of a multi-armed bandit. More specifically, we show that, in the blindly imitative weighted voter model of honey bees' waggle dance, the update rule through which this macro-agent learns is an RL algorithm that we coin Maynard-Cross Learning. Our analysis implies that a group of individuals following simple imitative strategies can be equivalent to a more complex learning entity, substantiating the idea that group-level intelligence may explain how seemingly irrational individual behaviors are selected in nature. Beyond biology, the framework offers new tools for analyzing economic and social systems where individuals imitate successful strategies, effectively participating in a collective learning process. Our findings may further inform the design of scalable RL-inspired collective systems in artificial domains.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 5, 2026

s3^3: Simple Scaling of Swarms via Cooperative Multi-agent RL

Groups can achieve more than individuals in the same amount of time, but only if their members coordinate: they must decide who works on what and what to share. However, this organization in multi-agent systems today usually comes from arbitrary, static harnesses designed a priori without adapting to agent behaviors or task specifications. We ask whether agents can instead learn to organize themselves. We introduce s3^3, the first multi-agent reinforcement learning method in which agents decide for themselves how long to work alone and when to share findings or read teammates' messages, with no predefined organization or roles. Our s3^3 agents learn to take different approaches, read each other's work, exhibit emergent roles that complement each other in the swarm, and generalize to bigger teams. We study both coordination, where agents must combine private information, and parallel exploration, where sharing discoveries can make search more efficient. With matched training and inference budgets, s3^3, swarms evaluated with twice as many agents as in training solve over 25×\times more coordination problems than the strongest baseline, and in exploration, communicating agents reduce repeated work by nearly 50% and outperform best-of-N by up to 9.4 percentage points. Rather than being designed in advance, s3^3 enables organization to emerge from a shared goal. This opens the door to capable systems built from many models that learn to work together.
Oct 18, 2026

A learner-free swarm approximates the explore-exploit equilibrium allocation: A self-organized attractor in place of reinforcement-learning machinery

Reinforcement learning (RL) solves the explore-exploit problem by training a learner on reward; its multi-agent, resource-sharing form has an equilibrium allocation as its optimum -- the ideal-free distribution (IFD), the Nash equilibrium of a congestion game. We show a minimal swarm approximates it with no learner at all. We present a decentralized, learner-free method for this problem: agents explore by heavy-tailed (Levy) flights, recruit neighbours to a discovery through a degree-normalized threshold cascade, and disperse as a patch crowds. The method drives the collective to the shape of the equilibrium allocation (pooled spatial matching slope 1.14, R^2=0.61) with no training, no stored parameters, and no reward in its dynamics; it reaches this as a self-organized attractor and holds it, re-finding it when the resources move -- though it reaches the shape, not the exact equilibrium, and stays measurably exploitable (Nash-gap 1.46). Coupling recruitment to movement causes the allocation: removing it collapses the matching (slope 0.006). Against Proximal Policy Optimization (PPO) learners (feedforward, centralized-critic, graph message-passing, and recurrent) trained in the same sensing-limited environment, the method at zero training is the only arm left unbiased w.r.t. the IFD gradient (slope ~1, CI containing 1, vs learners 0.69-0.97, all under-concentrating) and ties the best learner's harvest where resource is clustered, while the learner collects more where resource is scarce (0.33 vs 0.22) and holds a tighter per-capita intake. Learning buys precision and transfer across reward structures, not a better allocation shape. A companion paper develops the mechanism.
Jun 1, 2026

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple local incentives induce decentralized credit assignment, driving global planning without explicit orchestration or communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. Using modern Large Language Model (LLM) based agents, we show that, initialized with weak agents, the agent economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.