@inproceedings{bai-etal-2026-one,
    title = "One Cognitive Loop Is Enough: {SODA} unlocks Pure-Text Spatial Reasoning in Large Language Models",
    author = "Bai, Shunwen  and
      Zhang, Jiahuan  and
      Huang, Haoran  and
      Wang, Yurun  and
      Liu, Jiale  and
      Wu, Yanxi  and
      Yu, Ningzhe  and
      Gao, Yudong  and
      Cheng, Mingjun",
    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.1382/",
    pages = "29974--29996",
    ISBN = "979-8-89176-390-6",
    abstract = "Currently, large language models (LLMs) have significant limitations in spatial reasoning, particularly in the absence of visual input. To address this issue, we introduce SODA (Spatial OODA), which draws inspiration from the OODA cognitive loop (Observe, Orient, Decide, Act), originally designed to enhance human decision-making in dynamic environments. Specifically, we embed the OODA loop into multiple control tasks, generating the SPOD-143k dataset, and successfully integrate it into LLMs through a two-phase and spatia-aware training strategy (SFT and GRPO). Furthermore, to fill the gap in evaluating spatial reasoning in purely text-based LLMs, we introduce the SPOD-Bench benchmark, including multiple tasks divided into three levels of difficulty. Experimental results show that SODA significantly enhances the spatial reasoning capabilities of LLMs across testing scenarios including SPOD-Bench, SPACE and applications, providing a replicable and effective paradigm for improving the spatial cognition of LLMs."
}