Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

  • 类型：arxiv
  • 标识：2608.28122
  • 链接：https://arxiv.org/abs/2608.28122
  • 主分类：agent
  • 形态：survey
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：This survey examines agentic artifact creation, which is defined as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work, and formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted repair, and revalidating affected state after change.
  • OpenAlex ID：W7204854637
  • OpenAlex DOI：10.48550/arxiv.2608.28122
  • DOI：10.48550/arxiv.2608.28122
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2608.28122
  • OpenAlex更新：2026-09-02
  • 副分类：evaluation
  • 待LLM分类：否
  • 标题中文：Agentic Artifact Creation：系统、评估、原则与机遇
  • TLDR中文：本文综述了 agentic artifact creation，即有状态的构建过程，其中 AI 系统实体地构造或修改交付物，且中间观察结果会重定向后续工作；并提出了若干原则，使承诺与责任显式化、将反馈转化为针对性修复，以及在变更后重新验证受影响的状态。
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-31-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]