Emergent Collective Memory in Decentralized Multi-Agent AI Systems

TL;DR

This paper shows how decentralized multi-agent systems develop collective memory through individual memories and environmental traces, with phase transitions and density effects validated across various conditions.

Contribution

It introduces a novel mechanism for emergent collective memory in decentralized agents using environmental traces and validates phase transition predictions experimentally.

Findings

Memory improves performance by 68.7% over no-memory baselines.

Environmental traces alone fail without cognitive infrastructure.

Coordination via traces dominates above a critical density rho ~ 0.20.

Abstract

We demonstrate how collective memory emerges in decentralized multi-agent systems through the interplay between individual agent memory and environmental trace communication. Our agents maintain internal memory states while depositing persistent environmental traces, creating a spatially distributed collective memory without centralized control. Comprehensive validation across five environmental conditions (20x20 to 50x50 grids, 5-20 agents, 50 runs per configuration) reveals a critical asymmetry: individual memory alone provides 68.7% performance improvement over no-memory baselines (1563.87 vs 927.23, p < 0.001), while environmental traces without memory fail completely. This demonstrates that memory functions independently but traces require cognitive infrastructure for interpretation. Systematic density-sweep experiments (rho in [0.049, 0.300], up to 625 agents) validate our theoretical phase transition prediction. On realistic large grids (30x30, 50x50), stigmergic coordination dominates above rho ~ 0.20, with traces outperforming memory by 36-41% on composite metrics despite lower food efficiency. The experimental crossover confirms the predicted critical density rho_c = 0.230 within 13% error.