Skip to main content

Research Intelligence

ScienceView
Artificial Intelligence

Reimagining research papers as interactive and reliable AI agents.

| Source: Nature

Here we introduce Paper2Agent, an automated framework that converts research papers into artificial intelligence (AI) agents. Paper2Agent transforms research output from passive artefacts into active systems that accelerate use and discovery. Conventional research papers require readers to understand and adapt the paper's code, data and methods to their work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by converting a paper into an AI agent that functions a

Here we introduce Paper2Agent, an automated framework that converts research papers into artificial intelligence (AI) agents. Paper2Agent transforms research output from passive artefacts into active systems that accelerate use and discovery. Conventional research papers require readers to understand and adapt the paper's code, data and methods to their work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by converting a paper into an AI agent that functions as a virtual corresponding author, exposing its manuscript, supplementary materials, datasets, code and workflows as active, agent-native knowledge rather than static text. It analyses the paper and codebase using multiple agents to construct a model context protocol (MCP) server, then generates and runs tests to refine and increase robustness of the MCP. These paper MCPs can be connected to a chat agent (such as Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the paper. We demonstrate Paper2Agent's effectiveness through case studies. Paper2Agent created an agent that leveraged AlphaGenome 1 to interpret genomic variants and agents based on Scanpy 2 and TISSUE (transcript imputation with spatial single-cell uncertainty estimation) 3 to conduct single-cell and spatial transcriptomics analyses. We validate that these agents reproduce the results of the original papers and carry out novel user queries. Paper2Agent created multiple agents that collaborate to prioritize a causal gene for psoriasis. By turning static papers into interactive AI agents, Paper2Agent introduces a paradigm for knowledge dissemination and a collaborative ecosystem of AI co-scientists.

Read the original source →

Related Topics

Related Stories

Artificial Intelligence

Integrating cooperative breeding with reciprocity and culture extends Hamilton's rule to humans.

We study how kinship and reciprocity shape giving and child care support in societies with limited access to markets. Extending Hamilton's rule to incorporate reciprocity, we test it using behavioral data from dictator games and surveys in remote matrilocal and patrilocal villages of northeast India (N = 406 parents of young children). We replicate with data from urban Manila neighborhoods (N = 301) and the Solomon Islands (N = 624). Consistent with predictions, transfers to recipients increase

Continue reading
Artificial Intelligence

A microexon regulatory code reveals autism-linked genetic variation.

Neuronal microexons are a highly conserved class of alternative splicing events enriched in genes with critical functions in nervous system biology 1,2 . Microexon splicing is often disrupted in the brains of autistic individuals, and mice with microexon deficiencies display autism-like phenotypes 1,3,4 . However, the full landscape of microexons is not known, and the impact of genetic variation on these exons has not been systematically investigated. Here, through extensive transcriptome profil

Continue reading
Artificial Intelligence

Deep learning of fossil pollen morphology reveals 25,000 y of ecological change in eastern African grasslands.

Grass (Poaceae) pollen is largely overlooked in investigations of grassland evolution because the pollen of most species cannot be differentiated using traditional optical microscopy. However, the combination of superresolution microscopy and deep learning enables the capture and quantification of distinct morphological variation across the pollen of grass species. Using a semisupervised deep-learning strategy, we trained convolutional neural networks (CNNs) on superresolution images of known mo

Continue reading
Artificial Intelligence

Tyrosine phosphorylation unfolds nucleophosmin and disrupts its integration into the nucleolus.

Nucleophosmin (NPM1) is a multifunctional nucleolar protein essential for ribosome biogenesis, genome stability, and stress responses. Its integration into the nucleolus depends on its oligomerization and multivalent interactions that enable liquid-liquid phase separation (LLPS). Here, we investigate how tyrosine phosphorylation at Tyr17, Tyr29, and Tyr67 located within the interface between monomers at the N-terminal oligomerization domain regulates NPM1 structure and function. Replacing tyrosi

Continue reading
Artificial Intelligence

Human-artificial intelligence collaboration for comanaging epilepsy in real time.

One-third of the world's 70 million people with epilepsy have seizures uncontrolled by medication, and implantable devices are a promising treatment. These devices can detect impending seizures, missed medication and impaired cognition, but, like most medical devices, they cannot share this information with patients in real time. This is a missed opportunity for devices to learn from clinical events and teach patients how their behaviors affect their health. Here we present a device platform tha

Continue reading