Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse

2026-05-11

AI Summary

This work explores the development of generalist agents capable of operating across a diverse multiverse of games with varying rules, physics, and objectives, thereby advancing the pursuit of artificial general intelligence (AGI). It introduces a systematic framework encompassing datasets, models, interfaces, and evaluation benchmarks, and for the first time defines a five-level evolutionary pathway—from mastery in a single game to autonomous world creation—that addresses five fundamental trade-offs in current AGI research. By integrating large-scale foundation models, cross-game datasets, a unified evaluation protocol, and a co-evolutionary mechanism between agents and environments, this study establishes a novel paradigm and comprehensive blueprint for training and assessing truly general-purpose intelligent agents.

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.

Problem

• Generalist Game Players
• Foundation Models
• Game Multiverse
• Artificial General Intelligence
• Generalization

Innovation

• Generalist Game Player
• Foundation Models
• Game Multiverse
• Artificial General Intelligence
• End-to-End Framework