科学乌托邦？学术研究生态系统的闭环LLM模拟
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
浏览论文内容
中文总结 AI 辅助
本文提出SciUtopia，一种闭环LLM智能体模拟框架，用于模拟学术生态系统中的研究、评审与资助等过程，并通过大规模纵向模拟揭示了评审负担放大、探索策略平衡及资源不平等的涌现机制。
中文摘要 AI 辅助
科学进步源于一个纵向生态系统，其中研究人员、机构、资助机构、合作网络和科学文献共同演化。随着人工智能越来越多地参与到整个科学研究周期中，理解这些相互关联且不断演化的过程变得越来越重要。我们引入了SciUtopia，一个用于研究学术研究生态系统的持久化、闭环LLM智能体模拟框架。SciUtopia模拟了相互关联的科学过程，如研究方向选择、合作、投稿、同行评审、重新投稿、引用、资助和研究人员流失，同时保持跨模拟年份的演化状态。其可配置的机构机制和信息渠道为匹配的反事实实验和针对性干预提供了一个受控测试平台。在61个模拟世界中，SciUtopia模拟了来自8000个机构的超过40000名研究人员，产生了约400000个发表决策和120万条LLM生成的同行评审。利用这些纵向模拟，我们发现拒绝驱动的重新投稿显著放大了评审负担，其影响远超人口增长本身；谨慎的探索在引用影响、职业成功和长期主题多样性之间取得了平衡；即使在没有从早期狭窄获胜资助中检测到累积优势的情况下，资源不平等也可能出现。代码可在以下网址获取：此https URL。
英文摘要
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.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
- University of California, Los Angeles（加州大学洛杉矶分校）
- University of Chicago（芝加哥大学）
- William & Mary（威廉与玛丽学院）
机构由 AI 辅助整理，请以论文原文为准。
