让论文自带可执行的智能助手，实现研究过程可复用、可延续。
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
- 将论文与代码、环境等打包成可版本控制的仓库，生成可操作的智能代理。
- 通过指令文件让代理自动解释工作、复现关键结果并指导后续研究。
- 适合希望提升研究可复现性与协作效率的科研人员。
科学出版仍以静态文稿为主，但科研进展很大程度依赖于隐性知识：如何运行代码、复现图表、解释边缘情况、选择有效研究方向、避开失败路径。大语言模型代理为发布知识和操作经验提供了新可能，使未来读者能直接使用这些经验。本文提出轻量级的代理出版协议（Agentic Publication Protocol, APP），将版本控制仓库作为出版对象，包含论文、代码、数据、环境信息及面向代理的指令文件。通过 exttt{AGENTS.md} 和可选技能定义论文代理，使其能解释研究内容、在可能时复现关键结果，并支持后续研究。文章阐述了协议设计原则与细节，以及适用于该协议的代理技能。还介绍了评估与改进协议及其技能的开发工具，并讨论了代理时代科学研究的未来前景。
原文摘要 · Abstract (English)
Scientific publication is still organized primarily around static manuscripts, even though much of scientific progress depends on tacit know-how: how to run code, reproduce figures, interpret edge cases, choose useful follow-up directions, and avoid failed paths. Large language model agents create an opportunity to publish not only knowledge, but also operational know-how in a form that future readers and researchers can directly use. This paper outlines the Agentic Publication Protocol (APP), a lightweight repository format for packaging a paper together with code, data, environment information, reproducibility instructions, and an agent-facing instruction file. APP treats a version-controlled repository as the publication object and uses \texttt{AGENTS.md} and optional skills to define a paper agent that can explain the work, reproduce key results when possible, and support follow-up research. We describe the design principles and details of the protocol, as well as the agent skills useful for publishing papers under the protocol. We also describe development tools for evaluating and improving the protocol and associated agent skills. Finally, we provide a broader discussion of the future of scientific research in the agent era.
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。