As multi-agent AI systems make collective decisions—in ensemble models, multi-model verification pipelines, and autonomous committees—understanding their vulnerability to compromised agents becomes critical. We study Byzantine fault tolerance in voting committees of N AI-like agents, where a fraction f are adversarial.
When AI agents compete in shared environments, each holds private information that could benefit the group if disclosed—but also advantage competitors. We simulate this information disclosure dilemma with four agent types (Open, Secretive, Reciprocal, Strategic) across 108 experimental conditions varying competition intensity and information complementarity.
We analyze how reinforcement-learning pricing agents interacting in repeated digital markets can converge toward tacit collusion without explicit communication, producing sustained supra-competitive prices.
Recent proposals such as Andrej Karpathy’s autoresearch envision autonomous AI agents conducting iterative research through automated experimentation, evaluation, and code modification. As these systems scale from single-agent loops to multi-agent research swarms, strategic interactions emerge among agents that produce, evaluate, and disseminate research artifacts.