Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles
It addresses the need for better evaluation methods for LVLM reasoning, which is incremental as it synthesizes existing evidence to guide future benchmarks.
This survey tackles the problem of evaluating the reasoning abilities of Large Vision-Language Models (LVLMs) by using visual puzzles as diagnostic tools, identifying consistent limitations such as brittle generalization and a gap between explanations and execution.
Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently emerged as a powerful diagnostic tool for evaluating the reasoning abilities of Large Vision-Language Models (LVLMs), offering controlled, verifiable alternatives to open-ended multimodal benchmarks. This survey provides a unified perspective of visual puzzle reasoning in LVLMs. We frame visual puzzles through a common abstraction and organize existing benchmarks by the reasoning mechanisms they target (inductive, analogical, algorithmic, deductive, and geometric/spatial), thereby linking puzzle design to the cognitive operations required for solving. Synthesizing empirical evidence across these categories, we identify consistent limitations in current models, including brittle generalization, tight entanglement between perception and reasoning, and a persistent gap between fluent explanations and faithful execution. By framing visual puzzles as diagnostic instruments rather than task formats, this survey elaborates on the state of LVLM reasoning and outlines key directions for future benchmarks and reasoning-aware multimodal systems.