How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism

TL;DR

This paper explores how AI agents make decisions in network-effect games, revealing that historical data and its order significantly influence equilibrium outcomes, with AI showing persistent optimism under certain conditions.

Contribution

Introduces a novel workflow using LLM-based agents to study decision-making in network effects, highlighting the impact of historical data structure on convergence and equilibrium.

Findings

Agents fail to infer equilibrium without history

Ordered histories enable partial convergence under weak effects

Randomized history prevents convergence, causing persistent AI optimism

Abstract

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.