Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
2026-05-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors explain how humans can understand many different types of games, each with unique rules, as a special kind of intelligence. They describe how Artificial Intelligence (AI) is evolving from simple game-specific programs to more general AI that can play many games and even create new ones. Their work outlines four key areas—Dataset, Model, Harness, and Benchmark—that help track AI progress and the challenges to overcome. They propose a five-step plan leading to AI that can master and invent any game, moving toward true general intelligence.
Artificial General IntelligenceReinforcement LearningFoundation ModelsMultiverse of GamesDatasetModelBenchmarkGame AIGeneralist AgentTrade-offs
Authors
Kuan Zhang, Dongchen Liu, Qiyue Zhao, Tianyu Xin, Yue Su, Haisheng Wang, Han Yin, Hongbo Ma, Peize Li, Tianjun Gu, Xiangnan Wu, Xinran Zhang, Yongxuan Li, Zirong Chen, Yiming Li
Abstract
The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this singular physical existence into a multiverse of games, each governed by entirely different rules, aesthetics, physics, and objectives. This omni-reality adaptability is a hallmark of general intelligence. As Artificial Intelligence progresses towards Artificial General Intelligence, the multiverse of games has evolved from mere entertainment into the ultimate ground for training and evaluating AGI. The pursuit of this generality has unfolded across four eras: from environment-specific symbolic and reinforcement learning agents, to current large foundation models acting as generalist players, and toward a future creator stage where agent both creates new game worlds and continually evolves within them. We trace the full lifecycle of a generalist game player along four interdependent pillars: Dataset, Model, Harness, and Benchmark. Every advance across these pillars can be read as an attempt to break one of five fundamental trade-offs that currently bound the whole system. Building on this end-to-end view, we chart a five-level roadmap, progressing from single-game mastery to the ultimate creator stage in which the agent simultaneously creates and evolves within theoretical game multiverse. Taken together, our work offers a unified lens onto a rapidly shifting field,and a principled path toward the omnipotent generalist agent capable of seamlessly mastering any challenge within the multiverse of games, thereby paving the way for AGI.