将提示词转化为可操作的界面工具，支持创意设计中的灵活调整与迭代。
AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools
- 把用户意图具象为可直接操作的交互工具，提升创作灵活性。
- 实时展示多种意图解读与模型响应，帮助用户调整方向。
- 基于示例或已有工具生成新工具，适合交互设计与创意工作流研究者。
基于聊天的提示通常生成冗长的线性文本，难以探索和修正模糊意图，也不便于回溯或转向。AI-Instruments 通过三个核心原则实现突破：（1）将用户意图具象化为可复用的直接操作工具；（2）反映模糊意图的多重解读（意图内反思）及模型输出范围（响应内反思），辅助设计决策；（3）通过示例、结果或另一工具的推演来实例化新工具。系统还利用大语言模型建议、变化并优化新工具，使控制逻辑从内容自动生成，超越硬编码功能。我们展示了四个技术原型，应用于图像生成，并基于十二名参与者的定性反馈，验证了 AI-Instruments 在意图表达、直接操控与非线性迭代流程中应对模糊意图的有效性。
原文摘要 · Abstract (English)
Chat-based prompts respond with verbose linear-sequential texts, making it difficult to explore and refine ambiguous intents, back up and reinterpret, or shift directions in creative AI-assisted design work. AI-Instruments instead embody "prompts" as interface objects via three key principles: (1) Reification of user-intent as reusable direct-manipulation instruments; (2) Reflection of multiple interpretations of ambiguous user-intents (Reflection-in-intent) as well as the range of AI-model responses (Reflection-in-response) to inform design "moves" towards a desired result; and (3) Grounding to instantiate an instrument from an example, result, or extrapolation directly from another instrument. Further, AI-Instruments leverage LLM's to suggest, vary, and refine new instruments, enabling a system that goes beyond hard-coded functionality by generating its own instrumental controls from content. We demonstrate four technology probes, applied to image generation, and qualitative insights from twelve participants, showing how AI-Instruments address challenges of intent formulation, steering via direct manipulation, and non-linear iterative workflows to reflect and resolve ambiguous intents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。