The problem with traditional academic papers, according to the authors (18 page PDF), is that people need to read, understand and implement the data sets and code bases. They introduce a new product, Paper2Agent, that convers the paper into an AI agent that can be accessed by other AI systems and incorporated into other projects. Code (it's implemented as an AI skill that represents the paper as an MCP server) is availabel on GitHub, along with some examples. "Looking forward, just as many journals now require data and code availability sections, we anticipate the emergence of an 'agent availability' section that specifies whether and how the contribution has been embodied as an interactive agent." Related: my own article, The Present and Future Landscape of AI in Scholarly Publishing.
Today: Total: [Direct link] [Share]
