As companies race to deploy AI agents across customer service, coding, cybersecurity, and research workflows, a new question is emerging: is there such a thing as too many agents? The study finds that multi-agent AI systems have an optimal operating range — and that piling on more agents past that point can actually hurt performance rather than help it. The upshot for organizations experimenting with multi-agent deployments: the goal isn’t to build the biggest possible AI workforce, but the best-organized one. The paper, “Flag Game: Interpreting Decision Mechanisms of Bounded Social Agents,” was accepted for presentation at the AI4Good Workshop at ICML. It’s part of NTT Research’s broader push to understand the fundamental principles behind how intelligent systems — human or artificial — learn, reason, and collaborate.