Pursuing Minimal Sufficiency in Spatial Reasoning

ICLR 2026 Conference Submission14338 Authors

Keywords: spatial reasoning, agent, VLM

Abstract:

Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: \textit{inadequate} 3D understanding capabilities stemming from 2D-centric pre-training, and reasoning failures induced by \textit{redundant} 3D information.
To address these, we first construct a Minimal Sufficient Set (MSS) of information before answering a given question: a \textit{compact} selection of 3D perception results from \textit{expert models}. We introduce \textbf{MSSR} (Minimal Sufficient Spatial Reasoner), a dual-agent framework that implements this principle. A \textit{Perception Agent} programmatically queries 3D scenes using a versatile perception toolbox to extract sufficient information, including a novel \textbf{SOG} (Situated Orientation Grounding) module that robustly extracts language-grounded directions. A \textit{Reasoning Agent} then iteratively refines this information to pursue minimality, pruning redundant details and requesting missing ones in a closed loop until the MSS is curated.
Extensive experiments demonstrate that our method, by explicitly pursuing both sufficiency and minimality, significantly improves accuracy and achieves state-of-the-art performance across two challenging benchmarks. Furthermore, our framework produces interpretable reasoning paths, offering a promising source of high-quality training data for future models. Source code will be made publicly available.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 14338