Design Anything 如何在大規模設計項目中維持設計意圖一致
Design Anything, Design at Scale
Design Anything 透過意圖-執行圖和任務合約,在長期設計項目中維持設計意圖一致,提升約束滿足度及交付物完整性。其基準測試涵蓋 19 個設計領域的 228 項任務;使用 DeepSeek V4.1 Flash High 和 GPT-5.6 Sol High 時,分別滿足 85.0% 和 92.5% 的簡報事實約束,較同模型基線高 15.4% 和 14.4%。
Published on Oct 17
Authors:
,
,
,
,
,
,
,
,
Abstract
Design Anything uses an intent-execution graph and task contracts to maintain design alignment across long projects, improving constraint satisfaction and deliverable completeness over baseline agents.
As multimodal resources are transformed into media outputs, agentic AI is expected to stay aligned with design intent over long horizons. Designers follow briefs specifying goals, constraints, and deliverables, with later work building on earlier decisions. Recent work reuses design experience across tasks, yet alignment among artifacts within one project remains challenging. Agents therefore need to preserve and apply this intent across domains and as projects grow. We introduce Design Anything, a graph-based harness that preserves design intent outside the model and binds deliverables to the workflow steps that produce them through an intent-execution graph. A task contract retains constraints and decisions, selected designs become explicit inputs to later generations, and a deterministic controller uses bindings and execution records to check output types and counts, identify outstanding deliverables, and guide subsequent turns. We also introduce DesignAnything-Bench, with 228 tasks across 19 design domains, including 38 project families at scales of 6, 14, and 24 artifacts. With the LLM held fixed, Design Anything satisfies 85.0% and 92.5% of the brief's factual constraints with DeepSeek V4.1 Flash High and GPT-5.6 Sol High, respectively, exceeding the strongest same-model baselines by 15.4% and 14.4%. These gains reach 25.1% and 23.0% on 24-artifact tasks. Under each model, Design Anything leads or ties in constraint satisfaction in 18 of 19 domains. Professional designers also prefer its complete deliverable sets over those of same-model baselines in a blind evaluation.
View arXiv page View PDF Project page GitHub 2 Add to collection
Get this paper in your agent:
hf papers read 2610.24771
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/2610.24771 in a model README.md to link it from this page.
Datasets citing this paper 2
Gemus-AI/DesignAnything-Results
Viewer • Updated about 3 hours ago • 912 • 38
Gemus-AI/DesignAnything-Bench
Viewer • Updated about 3 hours ago • 682 • 31 • 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.24771 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