- Max-Planck-Institut fuer Quantenoptik; Munich Center for Quantum Science and Technology
- Leinweber Institute for Theoretical Physics, Stanford University
APP-260617-0000scientific-publicationRelease v1.0.0Listed Jun 17, 2026
Open in your agent
git clone --recurse-submodules --branch v1.0.0 https://github.com/XiaoliangQi/agentic-publication-protocol-dev.app.gitcd agentic-publication-protocol-dev.appclaudegit clone --recurse-submodules --branch v1.0.0 https://github.com/XiaoliangQi/agentic-publication-protocol-dev.app.gitcd agentic-publication-protocol-dev.appcodexThese commands clone the repository and initialize the AI agent in its directory. Ask the agent to explain methodology, clarify derivations, or reproduce figures. The repository supports Claude Code, Codex, and any agent that reads AGENTS.md.
To import this paper into another project, install the APP plugin and run /load-paper https://github.com/XiaoliangQi/agentic-publication-protocol-dev.app/releases/tag/v1.0.0.
Summary
Rather than publishing only a static paper, APP proposes a more reproducible,
informative, and interactive publication format. An APP publication is an
organized bundle of the research work: paper, code, data, environment
information, and related context, together with an AGENTS.md instruction file
that lets future readers interact with a faithful paper agent.
The goal is for scientific publications to carry not only knowledge, but also
know-how: the practical understanding needed to interpret, reproduce, and build
on the work, which has traditionally been difficult to transfer faithfully. The
paper defines the protocol, describes agent skills for preparing APP
publications, and reports a small compare-app evaluation in which APP paper
agents show stronger grounding and honesty than a general repository-aware agent.