arxiv:2507.07998

PyVision: Agentic Vision with Dynamic Tooling

Published on Jul 10

· Submitted by

stzhao on Jul 11

Upvote

Authors:

Shitian Zhao ,

Haoquan Zhang ,

Ming Li ,

Qilong Wu ,

Abstract

PyVision, an interactive framework, enables LLMs to autonomously create and refine Python-based tools for visual reasoning, achieving significant performance improvements across benchmarks.

AI-generated summary

LLMs are increasingly deployed as agents, systems capable of planning, reasoning, and dynamically calling external tools. However, in visual reasoning, prior approaches largely remain limited by predefined workflows and static toolsets. In this report, we present PyVision, an interactive, multi-turn framework that enables MLLMs to autonomously generate, execute, and refine Python-based tools tailored to the task at hand, unlocking flexible and interpretable problem-solving. We develop a taxonomy of the tools created by PyVision and analyze their usage across a diverse set of benchmarks. Quantitatively, PyVision achieves consistent performance gains, boosting GPT-4.1 by +7.8% on V* and Claude-4.0-Sonnet by +31.1% on VLMsAreBlind-mini. These results point to a broader shift: dynamic tooling allows models not just to use tools, but to invent them, advancing toward more agentic visual reasoning.