跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分49

Coding Agents 的圖像生成能力有多大?

How Far Can Coding Agents Go in Visual Generation?

AI 導讀

研究探討 Coding Agents 能以程式碼生成圖像到甚麼程度,並在涵蓋 200 個提示詞的 AgentDrawBench 上評估其零樣本繪圖能力。結果顯示,Agents 擅長保留結構及滿足精確的視覺約束,但感知豐富度有限;重建所得的視覺程式碼亦保留了大量可用於視覺問答的資訊,在部分領域的準確度高於原始圖像。研究還發現,Agents 在不同繪圖介面及視角下呈現一致的場景佈局。

正文

Published on Oct 13

Authors:

,

,

,

,

Abstract

Coding agents build images via executable programs, showing structured visual reasoning and consistent internal scene representations across drawing interfaces.

Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: general-purpose coding agents that construct images through executable programs. Our study of zero-shot drawing on AgentDrawBench, a 200-prompt benchmark, reveals a distinctive capability profile. Agents excel at preserving structure and satisfying precise visual constraints, achieving competitive results in domains where compositional accuracy matters more than photorealistic appearance, while remaining limited in perceptual richness. Their visual expressiveness varies with the drawing interface, and a qualitative study on reconstruction shows how procedural skills extracted from human demonstrations support different artistic media. We then examine code as an external visual language of thought: a structured, executable representation that agents can construct and inspect. We test it in visual question answering task and find reconstructed visual code retains substantial information for question answering and, in some domains, supports higher accuracy than the original image. These abilities raise a further question: do agents draw on a shared internal representation of scene content beyond a particular drawing program? We explore an internal visual language-of-thought hypothesis, in which a shared, compositionally structured representation supports visual operations across drawing languages. Cross-harness drawings and images assembled from independent single-pixel queries exhibit related layouts and tones. Agents also maintain self-generated room arrangements across viewpoints after visible drawings are removed. These results demonstrate that the coding agent would maintain a consistent and coherent world inside its imagine even before the harness gets involved and the generation starts.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.19025

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.19025 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.19025 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.19025 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co