研究库 论文知识库

内容库 / 论文

arXiv:2608.28122 · Agent 智能体

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

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
TLDR：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
副分类：evaluation
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-08-31-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Yannic Kilcher (YouTube) · RSS 摘要

笔记工程筛选 Round · 2026-08-01 · Inference + Agent Harness（v2 · 2026-08-04 重写）

笔记 Gradient Flow · RSS 摘要

笔记 Cool Papers · cs.CL (papers.cool) · RSS 摘要

笔记 ByteByteGo · RSS 摘要

笔记 Cameron R. Wolfe (Deep Learning Focus) · RSS 摘要

arXiv

2608.28122

TLDR

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

arXiv ↗ 中文全文