When LLMs Try to Reason: Experiments in Text and Vision-Based Abstraction | Towards Data Science

Can large language models learn to reason abstractly from just a few examples? In this piece, I explore this question by testing both text-based (o3-mini) and image-capable (gpt-4.1) models on abstract grid transformation tasks. These experiments reveal the extent to which current models rely on pattern matching, procedural heuristics, and symbolic shortcuts rather than robust generalization. Even with multimodal inputs, reasoning often breaks down in the face of subtle abstraction. The results offer a window into the current capabilities and limitations of in-context meta-learning with LLMs.