# Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding

DevFeed: [Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding](<https://devfeed.tech/articles/vision-as-a-tool-visual-harness-for-multimodal-agentic-coding-135118.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17797>)

Author: Haolin Yang, Wenshan Wu, Jin Jiang, Yu Cheng, Yan Xia, Ting Song, Yangyu Huang, Zhiliang Peng, Wenhui Wang, Hangbo Bao, Yuzhe Zhang, Wen-Da Wei, Tengchao Lv, Li Dong, Lei Cui, Furu Wei

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [harness](<https://devfeed.tech/tags/harness.md>), [image-to-3d](<https://devfeed.tech/tags/image-to-3d.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [svg](<https://devfeed.tech/tags/svg.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [tool](<https://devfeed.tech/tags/tool.md>), [vision](<https://devfeed.tech/tags/vision.md>)

## AI overview

Vision-as-a-Tool (VaaT) treats general-purpose multimodal language models as callable utilities for visual reasoning, allowing text-only coding agents to offload perception and vision-capable agents to augment it on demand. The authors implement this approach in VHarness, a framework with five atomic actions, and evaluate it on Image-to-HTML, Image-to-SVG, and Image-to-3D generation. They report improved visual fidelity and geometric accuracy for both text-only and multimodal coding agents. The supplied abstract does not detail the five actions or quantify the gains.

## Source excerpt

arXiv:2611.17797v1 Announce Type: new Abstract: Multimodal agentic coding requires robust visual reasoning to analyze observations and evaluate generated artifacts. Current frameworks largely rely on a Thinking-with-Images paradigm, where agents depend on their intrinsic vision to execute visually grounded tasks. However, this architectural coupling introduces a fundamental bottleneck. Agent performance remains strictly bounded by internal perceptual limitations. Furthermore, text-only agents lack native perception. Without specialized tools, they cannot perform visual reasoning. To overcome these constraints, we introduce the Vision-as-a-Tool (VaaT) paradigm. Prior visual tool-use merely manipulates images for an agent's intrinsic vision to read. In contrast, VaaT reframes general-purpose multimodal large language models (MLLMs) as callable external utilities. As a result, text-only agents can completely offload visual reasoning during agentic execution. Meanwhile, vision-capable agents can dynamically augment their native perception on demand. We instantiate this paradigm in VHarness, a unified framework driven by five atomic actions. We comprehensively evaluate VHarness across Image-to-HTML, Image-to-SVG, and Image-to-3D generation tasks. Experimental results demonstrate that VHarness consistently improves visual fidelity and geometric accuracy across both text-only and multimodal coding agents. These findings highlight that modularizing visual reasoning into callable utilities provides a flexible and scalable foundation for future agentic coding systems.