Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems

2026-10-01

AI Summary

This study addresses the unclear long-term co-evolutionary mechanisms among researchers, institutions, and literature within AI-mediated scientific ecosystems. To this end, it proposes SciUtopia, a pioneering persistent closed-loop large language model agent-based simulation framework that comprehensively models the entire research pipeline, including topic selection, collaboration, and peer review, while supporting counterfactual experiments, intervention testing, and cross-year dynamic state evolution. By generating million-scale review data through 40,000 agents, this work reveals critical patterns—such as how rejection-and-resubmission cycles exacerbate systemic burdens and how cautious exploration fosters career success—thereby providing a computational experimentation platform to inform science policy formulation.

Abstract

Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve. As AI becomes increasingly involved throughout the scientific research cycle, understanding these interconnected and evolving processes becomes increasingly important. We introduce SciUtopia, a persistent, closed-loop LLM-agent simulation framework for studying academic research ecosystems. SciUtopia models interconnected scientific processes such as research-direction choice, collaboration, submission, peer review, resubmission, citation, funding, and researcher attrition, while maintaining evolving states across simulated years. Its configurable institutional mechanisms and information channels provide a controlled testbed for matched counterfactual experiments and targeted interventions. Across 61 simulation worlds, SciUtopia simulates over 40,000 researchers from 8,000 institutions, producing around 400,000 publication decisions and 1.2 million LLM-generated peer reviews. Using these longitudinal simulations, we find that rejection-driven resubmission substantially amplifies reviewer burden beyond population growth alone, cautious exploration balances citation impact with career success and long-term topic diversity, and resource inequality can emerge even without detectable cumulative advantage from narrowly winning early funding. Code is available at https://github.com/Ahren09/ScienceUtopia.

Problem

• Academic Research Ecosystem
• Scientific Progress
• LLM Simulation
• Peer Review
• Resource Inequality

Innovation

• Closed-loop LLM simulation
• Academic research ecosystem
• Multi-agent framework
• Counterfactual experiments
• Longitudinal simulation