JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

TL;DR

JARVIS-1 is a multimodal, memory-augmented agent capable of understanding and executing over 200 diverse tasks in Minecraft, demonstrating significant improvements in long-horizon task completion over existing agents.

Contribution

The paper introduces JARVIS-1, a novel open-world agent that integrates multimodal perception, planning, embodied control, and memory to handle an extensive range of tasks in Minecraft.

Findings

Achieves nearly perfect performance on short-horizon tasks.

Surpasses state-of-the-art in long-horizon tasks by 5 times.

Successfully completes over 200 diverse tasks in Minecraft.

Abstract

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we develop JARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfit JARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences. JARVIS-1 is the existing most general agent in Minecraft, capable of completing over 200 different tasks using control and observation space similar to humans. These tasks range from short-horizon tasks, e.g., "chopping trees" to long-horizon tasks, e.g., "obtaining a diamond pickaxe". JARVIS-1 performs exceptionally well in short-horizon tasks, achieving nearly perfect performance. In the classic long-term task of $\texttt{ObtainDiamondPickaxe}$, JARVIS-1 surpasses the reliability of current state-of-the-art agents by 5 times and can successfully complete longer-horizon and more challenging tasks. The project page is available at https://craftjarvis.org/JARVIS-1