iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs
This addresses the limitation of VLMs in spatial reasoning for AI research, but it is incremental as it builds on existing benchmark methods.
The authors tackled the problem of Vision-Language Models (VLMs) struggling with spatial reasoning by introducing iVISPAR, an interactive benchmark based on sliding tile puzzles, and found that VLMs perform better on 2D tasks but still fall short of human performance, with results highlighting persistent gaps in visual alignment.
Vision-Language Models (VLMs) are known to struggle with spatial reasoning and visual alignment. To help overcome these limitations, we introduce iVISPAR, an interactive multimodal benchmark designed to evaluate the spatial reasoning capabilities of VLMs acting as agents. \mbox{iVISPAR} is based on a variant of the sliding tile puzzle, a classic problem that demands logical planning, spatial awareness, and multi-step reasoning. The benchmark supports visual 3D, 2D, and text-based input modalities, enabling comprehensive assessments of VLMs' planning and reasoning skills. We evaluate a broad suite of state-of-the-art open-source and closed-source VLMs, comparing their performance while also providing optimal path solutions and a human baseline to assess the task's complexity and feasibility for humans. Results indicate that while VLMs perform better on 2D tasks compared to 3D or text-based settings, they struggle with complex spatial configurations and consistently fall short of human performance, illustrating the persistent challenge of visual alignment. This underscores critical gaps in current VLM capabilities, highlighting their limitations in achieving human-level cognition. Project website: https://microcosm.ai/ivispar