Design Anything：用意图-执行图让 Agent 长流程设计不跑偏
Design Anything, Design at Scale
做 Agent 长任务的朋友看看这篇：把设计意图存图里、用确定性控制器核对交付物，19 个领域、228 个任务的基准测下来，同一模型约束满足率高出基线 14-25%。
arXiv 论文提出 Design Anything，一个基于图的框架，把设计意图保存在模型外部，通过意图-执行图将交付物绑定到工作流步骤。任务契约记录约束与决策，确定性控制器依据绑定和执行记录检查输出类型、数量并引导后续生成。配套的 DesignAnything-Bench 包含 228 个任务、19 个设计领域、38 个项目族（规模为 6、14、24 个交付物）。在固定 LLM 的条件下，DeepSeek V4.1 Flash High 和 GPT-5.6 Sol High 的事实约束满足率分别达到 85.0% 和 92.5%，比同模型最强基线高出 15.4% 和 14.4%；在 24 个交付物的任务上领先幅度扩大到 25.1% 和 23.0%。盲评中职业设计师也更偏好其完整交付物。
Design Anything, Design at Scale
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.
