@inproceedings{yu-etal-2026-i2e,
    title = "{I}2{E}: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing",
    author = "Yu, Jinghan  and
      Xiao, Junhao  and
      Zhu, Chenyu  and
      Li, Jiaming  and
      Li, Jia  and
      Deng, HanMing  and
      Wang, Xirui  and
      Jia, Guoli  and
      Li, Jianjun  and
      Bai, Xiang  and
      Zhou, Bowen  and
      Ma, Zhiyuan",
    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.2076/",
    pages = "44827--44850",
    ISBN = "979-8-89176-390-6",
    abstract = "Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require precise local control and complex multi-object spatial reasoning. This paradigm is severely limited by 1) the implicit coupling of planning and execution, 2) the lack of object-level control granularity, and 3) the reliance on unstructured, pixel-centric modeling. To address these limitations, we propose I2E, a novel ``Decompose-then-Action'' paradigm that revisits image editing as an actionable interaction process within a structured environment. I2E utilizes a Decomposer to transform unstructured images into discrete, manipulable object layers and then introduces a physics-aware Vision-Language-Action Agent to parse complex instructions into a series of atomic actions via Chain-of-Thought reasoning. Further, we also construct I2E-Bench, a benchmark designed for multi-instance spatial reasoning and high-precision editing. Experimental results on I2E-Bench and multiple public benchmarks demonstrate that I2E significantly outperforms state-of-the-art methods in handling complex compositional instructions, maintaining physical plausibility, and ensuring multi-turn editing stability."
}