How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism
This addresses a problem for researchers and practitioners in multi-agent AI systems by revealing that equilibrium outcomes depend on curated history, a novel insight with implications for strategic interactions in network-effect contexts.
The study tackled how AI agents make decisions in network-effect games, finding that without historical data they fail to infer equilibrium, and that ordered sequences enable partial convergence while randomized history disrupts it, with agents showing persistent 'AI optimism' under strong network effects.
Understanding decision-making in multi-AI-agent frameworks is crucial for analyzing strategic interactions in network-effect-driven contexts. This study investigates how AI agents navigate network-effect games, where individual payoffs depend on peer participatio--a context underexplored in multi-agent systems despite its real-world prevalence. We introduce a novel workflow design using large language model (LLM)-based agents in repeated decision-making scenarios, systematically manipulating price trajectories (fixed, ascending, descending, random) and network-effect strength. Our key findings include: First, without historical data, agents fail to infer equilibrium. Second, ordered historical sequences (e.g., escalating prices) enable partial convergence under weak network effects but strong effects trigger persistent "AI optimism"--agents overestimate participation despite contradictory evidence. Third, randomized history disrupts convergence entirely, demonstrating that temporal coherence in data shapes LLMs' reasoning, unlike humans. These results highlight a paradigm shift: in AI-mediated systems, equilibrium outcomes depend not just on incentives, but on how history is curated, which is impossible for human.