Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

ACL ARR 2026 January Submission5702 Authors

Keywords: Large Language Models, Spatial Reasoning, Policy Optimization

Abstract: LLMs have shown remarkable proficiency in general language understanding and reasoning. However, they consistently underperform in spatial reasoning that severely limits their application, particularly in embodied intelligence. Inspired by the success of hierarchical reinforcement learning, this paper introduces a novel method for hierarchical task decomposition in LLM spatial reasoning. Our approach guides LLMs to decompose complex tasks into manageable sub-tasks by identifying key intermediate states and generating simplified sub-environments. However, we identify that LLMs often fail to derive optimal intermediate states due to their insufficient spatial prior, leading to sub-optimal task decomposition. To address this limitation and enhance its planning capability, we propose a MCTS-Guided Group Relative Policy Optimization (M-GRPO). where we reformulate the UCT formula by incorporating the LLM’s prior predictive probabilities alongside its epistemic uncertainty. Furthermore, we implement a more fine-grained advantage function, enabling the model to learn optimal path planning. Experimental results demonstrate that our method substantially improves LLM performance on spatial tasks, including navigation, planning, and strategic games, achieving state-of-the-art results. This work paves the way for LLMs in real-world applications.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: NLP Applications, Machine Learning for NLP, Dialogue and Interactive Systems

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5702