Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Shengguang, Wang, Xiaohan, Zhang, Yuhui, Zhu, Hao, Yeung-Levy, Serena
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911337158803456
author Wu, Shengguang
Wang, Xiaohan
Zhang, Yuhui
Zhu, Hao
Yeung-Levy, Serena
author_facet Wu, Shengguang
Wang, Xiaohan
Zhang, Yuhui
Zhu, Hao
Yeung-Levy, Serena
contents Spatial reasoning in 3D scenes requires precise geometric calculations that challenge vision-language models. Visual programming addresses this by decomposing problems into steps calling specialized tools, yet existing methods rely on either fixed toolsets or speculative tool induction before solving problems, resulting in suboptimal programs and poor utilization of induced tools. We present Transductive Visual Programming (TVP), a novel framework that builds new tools from its own experience rather than speculation. TVP first solves problems using basic tools while accumulating experiential solutions into an Example Library, then abstracts recurring patterns from these programs into reusable higher-level tools for an evolving Tool Library. This allows TVP to tackle new problems with increasingly powerful tools learned from experience. On Omni3D-Bench, TVP achieves state-of-the-art performance, outperforming GPT-4o by 22% and the previous best visual programming system by 11%. Our transductively learned tools are used 5x more frequently as core program dependency than inductively created ones, demonstrating more effective tool discovery and reuse. The evolved tools also show strong generalization to unseen spatial tasks, achieving superior performance on benchmarks from SpatialScore-Hard collection without any testset-specific modification. Our work establishes experience-driven transductive tool creation as a powerful paradigm for building self-evolving visual programming agents that effectively tackle challenging spatial reasoning tasks. We release our code at https://transductive-visualprogram.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20934
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
Wu, Shengguang
Wang, Xiaohan
Zhang, Yuhui
Zhu, Hao
Yeung-Levy, Serena
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multiagent Systems
Spatial reasoning in 3D scenes requires precise geometric calculations that challenge vision-language models. Visual programming addresses this by decomposing problems into steps calling specialized tools, yet existing methods rely on either fixed toolsets or speculative tool induction before solving problems, resulting in suboptimal programs and poor utilization of induced tools. We present Transductive Visual Programming (TVP), a novel framework that builds new tools from its own experience rather than speculation. TVP first solves problems using basic tools while accumulating experiential solutions into an Example Library, then abstracts recurring patterns from these programs into reusable higher-level tools for an evolving Tool Library. This allows TVP to tackle new problems with increasingly powerful tools learned from experience. On Omni3D-Bench, TVP achieves state-of-the-art performance, outperforming GPT-4o by 22% and the previous best visual programming system by 11%. Our transductively learned tools are used 5x more frequently as core program dependency than inductively created ones, demonstrating more effective tool discovery and reuse. The evolved tools also show strong generalization to unseen spatial tasks, achieving superior performance on benchmarks from SpatialScore-Hard collection without any testset-specific modification. Our work establishes experience-driven transductive tool creation as a powerful paradigm for building self-evolving visual programming agents that effectively tackle challenging spatial reasoning tasks. We release our code at https://transductive-visualprogram.github.io/.
title Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2512.20934