AI RESEARCH
Limits of Imagery Reasoning in Frontier LLM Models
arXiv CS.AI
•
ArXi:2603.26779v1 Announce Type: cross Large Language Models (LLMs) have nstrated impressive reasoning capabilities, yet they struggle with spatial tasks that require mental simulation, such as mental rotation. This paper investigates whether equipping an LLM with an external ``Imagery Module'' -- a tool capable of rendering and rotating 3D models -- can bridge this gap, functioning as a ``cognitive prosthetic.'' We conducted experiments using a dual-module architecture in which a reasoning module (an MLLM) interacts with an imagery module on 3D model rotation tasks.