当 AI 编程助手被放进虚拟身体：机器也会「玩耍」吗？

Is this machine playing?

AI 导读

研究者把现代 AI 编程助手放进一座未知数字岛屿，充当虚拟身体的大脑，仅给出不含具体任务、奖励或活动的极简指令。在三十小时的运行中，该具身智能体爬山、把方块堆成塔、画曼陀罗、重新诠释运动，还对自己世界的物理规律做实验，并习得后来扩展其能力的技术。这些行为在十三个智能体间反复出现，却各自演化为不同历史；研究据此检验其是否符合经典的「玩耍」标准，并追问玩耍能否成为机器发展的一种模式。

正文 · 原文

View PDF HTML (experimental)

Abstract:We placed a modern AI coding assistant in an unintended role: as the mind of a body on an unknown digital island. With only a minimal instruction mentioning no specific task, reward, or activity, the machine started animating its virtual body. Across thirty-hour runs, the embodied AI agent climbed hills, stacked blocks into towers, drew mandalas, reinterpreted sports, ran experiments on the physics of its world, and learned techniques that later expanded what it could accomplish. These activities recurred across thirteen agents but diverged into distinct histories. We examine whether this behavior satisfies classical criteria for play and ask whether play can become a mode of machine development.

Comments:	13 pages of main text, 17 figures
Subjects:	Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2610.07130 [cs.AI]
	(or arXiv:2610.07130v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.07130 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Nathan Cloos [view email]
[v1] Mon, 5 Oct 2026 17:57:54 UTC (4,487 KB)

来源：arXiv cs.AI · arxiv.org