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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yu, Li, Wenwen, Dou, Yifan, Ye, Guangnan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917144069931008
author Liu, Yu
Li, Wenwen
Dou, Yifan
Ye, Guangnan
author_facet Liu, Yu
Li, Wenwen
Dou, Yifan
Ye, Guangnan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11943
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism
Liu, Yu
Li, Wenwen
Dou, Yifan
Ye, Guangnan
Multiagent Systems
Artificial Intelligence
General Economics
Economics
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.
title How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism
topic Multiagent Systems
Artificial Intelligence
General Economics
Economics
url https://arxiv.org/abs/2512.11943