Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

TL;DR

Lumine is a pioneering open recipe for creating generalist agents capable of performing complex, hours-long tasks in 3D open worlds using a unified perception, reasoning, and action framework powered by vision-language models.

Contribution

It introduces Lumine, the first comprehensive approach to develop generalist agents in 3D open worlds, demonstrating strong zero-shot cross-game generalization without fine-tuning.

Findings

Successfully completes five-hour main storyline in Genshin Impact

Achieves zero-shot performance in Wuthering Waves and Honkai: Star Rail

Operates in real-time with adaptive reasoning and multi-modal tasks

Abstract

We introduce Lumine, the first open recipe for developing generalist agents capable of completing hours-long complex missions in real time within challenging 3D open-world environments. Lumine adopts a human-like interaction paradigm that unifies perception, reasoning, and action in an end-to-end manner, powered by a vision-language model. It processes raw pixels at 5 Hz to produce precise 30 Hz keyboard-mouse actions and adaptively invokes reasoning only when necessary. Trained in Genshin Impact, Lumine successfully completes the entire five-hour Mondstadt main storyline on par with human-level efficiency and follows natural language instructions to perform a broad spectrum of tasks in both 3D open-world exploration and 2D GUI manipulation across collection, combat, puzzle-solving, and NPC interaction. In addition to its in-domain performance, Lumine demonstrates strong zero-shot cross-game generalization. Without any fine-tuning, it accomplishes 100-minute missions in Wuthering Waves and the full five-hour first chapter of Honkai: Star Rail. These promising results highlight Lumine's effectiveness across distinct worlds and interaction dynamics, marking a concrete step toward generalist agents in open-ended environments.