@inproceedings{zhang-etal-2026-embodied,
    title = "Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks",
    author = "Zhang, Wenqi  and
      Wang, Mengna  and
      Liu, Gangao  and
      Xu, Huixin  and
      Jiang, Yiwei  and
      Shen, Yongliang  and
      Hou, Guiyang  and
      Zheng, Zhe  and
      Zhang, Hang  and
      Li, Xin  and
      Liu, Jiajun  and
      Lu, Weiming  and
      Li, Peng  and
      Zhuang, Yueting",
    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.1910/",
    pages = "41178--41207",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains, where the agent must continuously interact with environments and process observation-action interleaved trajectories, remains largely unexplored. We present Embodied-Reasoner, a reasoning model for interactive embodied tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training recipe that progressively enhances the model{'}s capabilities through imitation learning, rejection sampling tuning on self-exploration trajectories, and reflection tuning. The evaluation shows that our model significantly outperforms advanced visual reasoning models, e.g., exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9{\%}, 24{\%}, and +13{\%}. Analysis reveals that our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world testing further validates the effectiveness of our approach."
}