One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models

ACL ARR 2026 January Submission9553 Authors

Keywords: Spatial Cognition, LLMs, OODA

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.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: NLP,LLM,Spatial cognition

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 9553