GenClaw: 代码驱动的智能体图像生成
GenClaw: Code-Driven Agentic Image Generation
AI总结：
提出GenClaw，一种代码驱动的智能体图像生成范式，通过概念构思、代码草图绘制和纹理补充三个阶段，将黑盒图像生成转变为可控、可解释的分阶段过程。
摘要：
图像生成模型已从基于文本的像素合成演变为具备视觉理解和工具调用能力的多模态智能体。然而，现有智能体仍受制于底层黑盒图像模型。其工作流程陷入重复的提示重写循环以改进生成，缺乏直接操控画布的机制。本质上，LLMs作为精确视觉构建的“画笔”的潜力尚未被充分挖掘。本文提出GenClaw，一种代码驱动的智能体图像生成范式，使智能体像人类艺术家一样创作：先构思，再素描，最后上色。具体而言，智能体首先通过搜索和推理构建概念知识和上下文。然后利用代码（如SVG、HTML、ThreeJS）渲染可执行的视觉草图。最后，使用图像生成模型补充纹理、材质和逼真度。在此工作流中，代码作为连接语言推理和像素合成的可控中间画布，无缝集成程序逻辑与生成模型的视觉表现力。通过将图像生成从黑盒范式转变为类似真实人类创作的分阶段过程，GenClaw朝着高度可控和可解释的视觉生成系统迈出了一步。
英文摘要：
Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existing agents remain at the mercy of underlying black-box image models. Their workflow is trapped in a repetitive cycle of prompt rewriting for generation refinement, leaving them with no mechanism to directly manipulate the canvas. In essence, the potential of LLMs to serve as a genuine "brush" for precise visual construction remains largely untapped. In this paper, we propose GenClaw, a code-driven agentic image generation paradigm that empowers the agent to create like a human artist: first conceptualizing, then sketching, and finally coloring. Specifically, the agent first constructs the conceptual knowledge and context through search and reasoning. It then utilizes code (e.g., SVG, HTML, ThreeJS) to render executable visual sketches. Finally, it employs an image generation model to supplement textures, materials, and photorealism. In this workflow, code serves as a controllable intermediate canvas bridging linguistic reasoning and pixel synthesis, seamlessly integrating programmatic logic with the visual expressiveness of generative models. By transforming image generation from a black-box paradigm into a staged process akin to authentic human creation, GenClaw offers a step toward for highly controllable and interpretable visual generation systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
