English

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

Artificial Intelligence 2026-03-04 v2

Abstract

Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent work extending this idea to visual domains using Vision-Language Models (VLMs). However, a rigorous comparison with methods that plan directly with VLMs is missing, due to a lack of visual benchmarks that support symbolic planning. We present ViPlan, the first open-source benchmark for comparing VLM-grounded symbolic approaches (VLM-as-grounder) with direct VLM planning methods (VLM-as-planner). ViPlan introduces a series of increasingly challenging tasks in two visual domains: a visual variant of the classic Blocksworld planning problem and a simulated household robotics environment. We find VLM-as-grounder methods to outperform direct VLM planning in Blocksworld (solving 46% of the tasks against 9%), where image grounding is both crucial and accurate. However, in the household robotics tasks, where linguistic knowledge helps, VLM-as-planner methods are greatly superior to VLM-as-grounder approaches (solving 34% of the tasks against 5%), which are hindered by partial observability. Thus, ViPlan domains capture fundamental shortcomings of both planning approaches, which we further diagnose with a qualitative failure analysis. Finally, across methods, we observe no consistent benefit from Chain-of-Thought prompting, suggesting persistent limitations in current VLMs' visual reasoning abilities.

Keywords

Cite

@article{arxiv.2505.13180,
  title  = {ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models},
  author = {Matteo Merler and Nicola Dainese and Minttu Alakuijala and Giovanni Bonetta and Pietro Ferrazzi and Yu Tian and Bernardo Magnini and Pekka Marttinen},
  journal= {arXiv preprint arXiv:2505.13180},
  year   = {2026}
}

Comments

8 pages, 5 figures and 1 table in the main text; 50 pages, 16 figures and 19 tables including supplementary material

R2 v1 2026-07-01T02:22:02.145Z