Swarm-Intelligence

Rosy barbs and tiger barbs have markedly different individual swimming patterns, yet form cohesive mixed-species schools by matching speed through local interactions.

A honeybee-inspired study compares centrally directed organisations with decentralized groups whose members allocate work through local communication and differing behavioural thresholds.

A new preprint examines how pairs of homing pigeons establish leader and follower roles when navigating with unfamiliar partners. The work matters because it reveals how distributed groups can rapidly settle coordination roles without a central authority or an established social history.

Research published in Behavioral Ecology and Sociobiology used drone footage and trajectory modelling to infer how Tibetan antelopes coordinate while moving.

A mathematical study of leaderless collectives found that efficient groups need only a small number of persistent risk-takers to explore during poor conditions, while the majority wait for favourable signals.

A new preprint examines how goldfish use two forms of social information—the number of fish in a shoal and how actively they are moving—when deciding which group to join.

This paper proposes “Embodied Collective Intelligence,” where robot teams share world memory, task progress, and skill experience without becoming a centralized super-agent.

Pentest Swarm AI uses a shared blackboard, pheromone-weighted findings, and decentralized agent triggers to let attack paths emerge instead of following a fixed pipeline.

This funding call frames AI safety as a population-level problem involving collusion, cascading failures, emergent communication, and collective capabilities. This closes 9-August-2026.

Palladyne AI says its SwarmOS software will be tested with U.S. Army warfighters to coordinate heterogeneous unmanned systems without relying on centralized infrastructure.