@inproceedings{tabassum-etal-2025-mmplanner,
    title = "{MMP}lanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning",
    author = "Tabassum, Afrina  and
      Guo, Bin  and
      Ma, Xiyao  and
      Eldardiry, Hoda  and
      Lourentzou, Ismini",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1011/",
    doi = "10.18653/v1/2025.findings-emnlp.1011",
    pages = "18623--18639",
    ISBN = "979-8-89176-335-7",
    abstract = "Multimodal Procedural Planning (MPP) aims to generate step-by-step instructions that combine text and images, with the central challenge of preserving object-state consistency across modalities while producing informative plans. Existing approaches often leverage large language models (LLMs) to refine textual steps; however, visual object-state alignment and systematic evaluation are largely underexplored.We present MMPlanner, a zero-shot MPP framework that introduces Object State Reasoning Chain-of-Thought (OSR-CoT) prompting to explicitly model object-state transitions and generate accurate multimodal plans. To assess plan quality, we design LLM-as-a-judge protocols for planning accuracy and cross-modal alignment, and further propose a visual step-reordering task to measure temporal coherence.Experiments on RecipePlan and WikiPlan show that MMPlanner achieves state-of-the-art performance, improving textual planning by $+6.8\%$, cross-modal alignment by $+11.9\%$, and visual step ordering by $+26.7\%$."
}