@inproceedings{zhang-etal-2025-knowing,
    title = "Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making",
    author = "Zhang, Chunhui  and
      Ouyang, Zhongyu  and
      Diao, Xingjian  and
      Liu, Zheyuan  and
      Vosoughi, Soroush",
    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.1042/",
    doi = "10.18653/v1/2025.findings-emnlp.1042",
    pages = "19144--19155",
    ISBN = "979-8-89176-335-7",
    abstract = "Modern embodied AI uses multimodal large language models (MLLMs) as policy models, predicting actions from final-layer hidden states. This widely adopted approach, however, assumes that monolithic last-layer representations suffice for decision-making{---}a structural simplification at odds with decades of cognitive science, which highlights the importance of distributed, hierarchical processing for perception and action. Addressing this foundational asymmetry, we introduce a hierarchical action probing method that explicitly aggregates representations from all layers, mirroring the brain{'}s multi-level organization. Experiments reveal that early layers facilitate spatial grounding, middle layers support contextual integration, and later layers enable abstract generalization{---}which shows MLLMs inherently encode distributed action-relevant structures. These layer-wise features are integrated by a lightweight probe for spatial reasoning and contextual understanding, without costly backbone fine-tuning. This hierarchical solution shows significant improvements over standard last-layer embodied models in physical simulators, achieving a 46.6{\%} success rate and a 62.5{\%} gain in spatial reasoning tasks. These findings challenge conventional assumptions in embodied AI, establishing hierarchical probing as a principled alternative grounded in both cognitive theory and empirical evidence."
}