Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions
This provides a new benchmark for assessing adaptable decision-making in AI, addressing a gap in evaluating interconnected real-world challenges, though it is incremental as it builds on existing simulation and benchmarking efforts.
The authors tackled the challenge of evaluating holistic decision-making in AI by introducing Mini Amusement Parks (MAPs), a simulator for business management, and found that humans outperform state-of-the-art LLM agents by 6.5x on easy mode and 9.8x on medium mode.
Despite rapid progress in artificial intelligence, current systems struggle with the interconnected challenges that define real-world decision making. Practical domains, such as business management, require optimizing an open-ended and multi-faceted objective, actively learning environment dynamics from sparse experience, planning over long horizons in stochastic settings, and reasoning over spatial information. Yet existing human--AI benchmarks isolate subsets of these capabilities, limiting our ability to assess holistic decision-making competence. We introduce Mini Amusement Parks (MAPs), an amusement-park simulator designed to evaluate an agent's ability to model its environment, anticipate long-term consequences under uncertainty, and strategically operate a complex business. We provide human baselines and a comprehensive evaluation of state-of-the-art LLM agents, finding that humans outperform these systems by 6.5x on easy mode and 9.8x on medium mode. Our analysis reveals persistent weaknesses in long-horizon optimization, sample-efficient learning, spatial reasoning, and world modelling. By unifying these challenges within a single environment, MAPs offers a new foundation for benchmarking agents capable of adaptable decision making. Code: https://github.com/Skyfall-Research/MAPs