While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smaller, more deployable models offers an efficient path to strong performance, but this is hampered by a major bottleneck: the absence of high-quality, step-by-step reasoning data. To address this data-efficiency gap, we introduce SpatialTraceGen, a framework to distill the reasoning processes of a large teacher model into a high-quality dataset of multi-hop, multi-tool reasoning traces. A key innovation is our automated Verifier, which scalably ensures the fidelity of each reasoning step, providing a cost-effective alternative to manual human annotation. On the CLEVR-Humans benchmark, this verifier-guided process improves the average quality score of traces by 17\% while reducing quality variance by over 40\%. SpatialTraceGen delivers a dataset of expert traces, providing the structured, step-by-step examples of tool use necessary for effective fine-tuning and sample-efficient offline reinforcement learning.
@article{arxiv.2511.00054,
title = {SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation},
author = {Gio Huh and Dhruv Sheth and Rayhan Zirvi and Frank Xiao},
journal= {arXiv preprint arXiv:2511.00054},
year = {2025}
}
Comments
Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Efficient Reasoning