Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara, Jayeon Park, Ernesto Gabriel Hernández Montoya, Chen Bo Calvin Zhang, Bin Hu, Yunzhong He, Bing Liu, Rakshith Sharma Srinivasa

Track: long paper (up to 8 pages)

Keywords: Think with images, Multi-Modal, MLLM, Vision Tool Use, Reasoning

TL;DR: We present VisualToolBench, the first vision tool-use reasoning benchmark that requires model think with images.

Abstract: Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient visual cues. Beyond static visual perception, MLLMs must also think with images: dynamically transforming visual content and integrating it with other tools to solve complex tasks. However, this shift from treating vision as passive context to a manipulable cognitive workspace remains underexplored. Most existing benchmarks still follow a think about images paradigm, where images are regarded as static inputs. To address this gap, we introduce VisualToolBench, a visual tool-use reasoning benchmark that rigorously evaluates MLLMs’ ability to perceive, transform, and reason across complex visual–textual tasks under the think with images paradigm. VisualToolBench comprises 1,204 challenging, open-ended vision tasks (603 single-turn, 601 multi-turn) spanning across five diverse domains, each paired with detailed rubrics to enable systematic evaluation. Our evaluation shows that current MLLMs struggle with tasks requiring effective integration of vision and general-purpose tools. Even the strongest model (Gemini-3-pro) reaches only 27.39% pass rate. We further observe divergent tool-use behaviors, with OpenAI models (such as GPT-5) benefiting from diverse image manipulations while Gemini models (such as Gemini-2.5-pro) shows no improvement. By introducing the first benchmark centered on think with images, VisualToolBench offers critical insights for advancing visual intelligence in MLLMs.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 28