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

arXiv: https://arxiv.org/abs/2610.01257 · HTML: https://mlsanity.com/paper/2610.01257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Delving into LLM-assisted writing in biomedical publications through excess vocabulary](https://mlsanity.com/paper/2406.07016/) (2024)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [ResearchTown: Simulator of Human Research Community](https://mlsanity.com/paper/2412.17767/) (2024)
- [Empirical evidence of Large Language Model's influence on human spoken communication](https://mlsanity.com/paper/2409.01754/) (2024)
- [Tradition and Innovation in Scientists' Research Strategies](https://mlsanity.com/paper/1302.6906/) (2013)
- [Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences](https://mlsanity.com/paper/2510.13201/) (2025)
- [Early-career setback and future career impact](https://mlsanity.com/paper/1903.06958/) (2019)
- [BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?](https://mlsanity.com/paper/2510.18003/) (2025)
- [MASCOT: Multi-Agent Socio-Collaborative Companion Systems](https://mlsanity.com/paper/2601.14230/) (2026)
- [UniSD: Towards a Unified Self-Distillation Framework for Large Language Models](https://mlsanity.com/paper/2605.06597/) (2026)
- [Divergent LLM Adoption and Heterogeneous Convergence Paths in Research Writing](https://mlsanity.com/paper/2504.13629/) (2025)
- [SciEvo: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis](https://mlsanity.com/paper/2410.09510/) (2024)
- [CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences](https://mlsanity.com/paper/2512.10918/) (2025)
- [Can Large Language Models Forecast What Researchers Study Next?](https://mlsanity.com/paper/2609.00747/) (2026)
- [Reviewers' ratings and bibliometric indicators: hand in hand when assessing over research proposals?](https://mlsanity.com/paper/1307.0110/) (2013)

## Abstract (arXiv)

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.