arXiv:2606.27386v1 Announce Type: cross Abstract: 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 pap
The proliferation of advanced AI agents, particularly large language models, provides the technical capability to move beyond static scientific publication formats.
Modernizing scientific publication to include operational know-how via agentic protocols could significantly accelerate research, improve reproducibility, and democratize access to practical scientific methods.
Scientific publications could evolve from static documents into dynamic, executable packages that directly integrate tacit knowledge and operational code.
- · AI researchers
- · Reproducibility advocates
- · Open science platforms
- · AI agent developers
- · Traditional academic publishers
- · Researchers reliant on opaque methods
Scientific outputs become more directly actionable and verifiable through integrated agentic capabilities.
The pace of scientific discovery and technological innovation accelerates due to enhanced knowledge transfer and reproducibility.
New forms of intellectual property and collaboration models emerge around executable scientific 'know-how' packages.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI