TraversalBench: Challenging Paths to Follow for Vision Language Models
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Abstract (arXiv)
Vision-language models (VLMs) perform strongly on multimodal benchmarks, but their ability to follow complex visual paths remains under-tested. We introduce TraversalBench, a controlled benchmark for exact visual path traversal. Each instance contains a continuous polyline with a unique start marker and labeled vertices; models must recover the ordered sequence encountered from start to finish. The benchmark balances self-intersection count, tortuosity, vertex count, and nearby confounding lines while limiting reliance on OCR, world knowledge, or open-ended planning. We find that self-intersections are the dominant source of difficulty. A first-crossing analysis localizes failures to crossing points: performance is stable before the first crossing, then drops sharply when the model must resolve the correct continuation. Nearby confounders have weaker but compounding effects, and an auxiliary reading-order benchmark reveals a consistent left-to-right bias. Together, these results characterize how VLMs perceive and fail on visual paths. Finally, we position TraversalBench as a new contribution to the growing line of sustained and precise visual grounding benchmarks for VLMs. Code, benchmark data, and rendered examples are available at https://github.com/clarapetrova/traversalbench.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 14 of its 31 references that are in the map. First posted on arXiv 13 Apr 2026.
Builds on
14 of 31 references.
Closest ancestors · 5
Same direction, newest first
- 2025VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs4 Jul
- 2025Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images19 Feb
- 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem31 Oct
- 2024Can We Talk Models Into Seeing the World Differently?14 Mar
- 2023Teaching CLIP to Count to Ten23 Feb
Other references · 9
- 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 642
- 2018TallyQA: Answering Complex Counting Questionscited by 153
- 2025See What You Are Told: Visual Attention Sink in Large Multimodal Modelscited by 132
- 2025VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledgecited by 55
- 2024Unveiling Visual Perception in Language Models: An Attention Head Analysis Approachcited by 35
- 2025Can Large Vision Language Models Read Maps Like a Human?cited by 30
- 2025Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Modelscited by 22
- 2025Visual Graph Question Answering with ASP and LLMs for Language Parsingcited by 2
- 2025Knot So Simple: A Minimalistic Environment for Spatial Reasoningcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
- 2025VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors
- 2024Evaluating Vision-Language Models as Evaluators in Path Planning
- 2024UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
- 2023Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
- 2025PairBench: Are Vision-Language Models Reliable at Comparing What They See?
- 2025CompareBench: A Benchmark for Visual Comparison Reasoning in Vision-Language Models
- 2024Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning