智能体工件创建：系统、评估、原则与机遇
Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
- Zhejiang University（浙江大学）
- University of Science and Technology of China（中国科学技术大学）
- Tsinghua University（清华大学）
- The University of Hong Kong（香港大学）
- The University of Sydney（悉尼大学）
- Sun Yat-sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本综述研究智能体工件创建，分析259项相关研究，明确其定义与功能结构，制定相关原则并识别维持控制的机遇。
AI中文摘要：
生成式模型可将自然语言提示转化为图像、文本、代码及其他内容，降低草稿与组件的生成成本，其实际影响日益取决于这些内容能否成为完整可靠的交付物。本综述研究智能体工件创建，将其定义为有状态的构建过程，其中AI系统实质性构建或修订交付物，且中间观察结果会引导后续工作。从功能上看，该过程关联工件的操作表示、构建策略与运行时验证，其反馈可引导后续行动。我们查阅了截至2026年8月20日的259项研究，其中230个系统符合该定义，29个为智能体工件构建的基准。我们对比了6类工件，再将应用场景与评估实践作为独立维度分析。各类工件的构建挑战不仅反映模态，还体现决策的耦合紧密程度，以及故障在可修复时是否可见。分解可降低局部复杂度，但会增加协调与重组成本；若学习到的评判器与生成器偏好或盲点一致，其提供的独立证据可能极少。我们制定了明确承诺与责任、将反馈转化为针对性修复、变更后重新验证受影响状态的原则，还识别了随着工件、创建者意图与构建系统演变，维持连贯可问责控制的机遇，整理后的论文列表可在该https URL获取。
英文摘要：
Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. Their practical impact increasingly depends on whether those pieces can become complete, dependable deliverables. This survey examines agentic artifact creation, which we define as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work. Functionally, the process links an operational representation of the artifact, a construction policy, and runtime verification whose feedback can redirect later actions. We reviewed 259 works available through August 20, 2026: 230 systems meeting this definition and 29 benchmarks of agentic artifact construction. We compare six artifact families, then analyze application settings and evaluation practice as separate dimensions. Across families, construction challenges reflect not only modality but also how tightly decisions are coupled and whether failures become visible while they remain repairable. Decomposition can reduce local complexity while increasing coordination and reassembly costs. Learned judges may add little independent evidence when they share the generator's preferences or blind spots. We formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted repair, and revalidating affected state after change. We also identify opportunities for sustaining coherent, accountable control as artifacts, creator intent, and construction systems evolve. A curated paper list is available at https://github.com/GeminiLight/awesome-agentic-artifact-creation.
