@inproceedings{qi-etal-2026-e,
    title = "{E}-{V}i{C}: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence",
    author = "Qi, Junbo  and
      Zhang, Yi  and
      Ni, Hanchu  and
      Liu, Che  and
      Yao, Zhimin  and
      Yang, Ruilin  and
      Ren, Xiancong  and
      Wen, Liangjian  and
      Ge, Wei  and
      Ieiri, Yuya  and
      Yoshie, Osamu  and
      Dai, Yong  and
      Ju, Xiaozhu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1870/",
    pages = "40283--40303",
    ISBN = "979-8-89176-390-6",
    abstract = "Precise spatial reasoning is fundamental to embodied intelligence, yet current Vision-Language Models (VLMs) remain bottlenecked by text-based Chain-of-Thought (CoT) that relies solely on textual reasoning trajectories, often bypassing active engagement with fine-grained visual details. To address this, we present E-ViC (Embodied Visual Chain), a framework that moves reasoning beyond text and directly into the visual domain. By formulating visual operations (e.g., zooming, marking) as executable primitives, E-ViC transforms perception from static prediction into an active verification process. Distinct from approaches relying on supervised step-wise trajectories, E-ViC is trained via an agentic reinforcement learning paradigm. This enables the model to autonomously discover optimal policies, leading to the emergence of human-like ``look-and-confirm'' strategies driven solely by task-level rewards. To facilitate this, we curate a comprehensive 24.4K-sample dataset covering diverse embodied tasks. By grounding reasoning in pixel-level interactions, E-ViC reframes spatial intelligence as a verifiable, tool-using capability. Extensive evaluations on external benchmarks demonstrate that our approach consistently outperforms strong VLM baselines with an average gain of 10.1{\%}."
}