PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
Abstract
PixelCraft, a multi-agent system, enhances visual reasoning in multimodal large language models by integrating high-fidelity image processing and flexible reasoning through a dynamic workflow and image memory.
Structured images (e.g., charts and geometric diagrams) remain challenging for multimodal large language models (MLLMs), as perceptual slips can cascade into erroneous conclusions. Intermediate visual cues can steer reasoning; however, existing cue-based methods are constrained with low-fidelity image processing and linear, rigid reasoning patterns, limiting their effectiveness on complex structured-image tasks. In this paper, we propose PixelCraft, a novel multi-agent system for high-fidelity image processing and flexible visual reasoning on structured images. The system comprises a dispatcher, a planner, a reasoner, critics, and a set of visual tool agents. To achieve high-fidelity processing, we construct a high-quality corpus and fine-tune an MLLM into a grounding model, whose pixel-level localizations are integrated with traditional computer vision (CV) algorithms in tool agents. Building on this foundation, PixelCraft facilitates flexible visual reasoning through a dynamic three-stage workflow of tool selection, agent discussion, and self-criticism. Moreover, unlike prior linear reasoning patterns that simply append historical images, PixelCraft maintains an image memory to allow the planner to adaptively revisit earlier visual steps, explore alternative reasoning branches, and dynamically adjust the reasoning trajectory during discussion. Extensive experiments on challenging chart and geometry benchmarks demonstrate that PixelCraft significantly improves visual reasoning performance for advanced MLLMs, setting a new standard for structured image reasoning. Our code will be available at https://github.com/microsoft/PixelCraft.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Simple o3: Towards Interleaved Vision-Language Reasoning (2025)
- WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent (2025)
- GeoSketch: A Neural-Symbolic Approach to Geometric Multimodal Reasoning with Auxiliary Line Construction and Affine Transformation (2025)
- SIFThinker: Spatially-Aware Image Focus for Visual Reasoning (2025)
- Decoupling Reasoning and Perception: An LLM-LMM Framework for Faithful Visual Reasoning (2025)
- An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing (2025)
- LLM-I: LLMs are Naturally Interleaved Multimodal Creators (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
