Reimagining research papers as interactive and reliable AI agents

Reimagining research papers as interactive and reliable AI agents

Here we introduce Paper2Agent, an automated framework that converts research papers into artificial intelligence 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 server, then generates and runs tests to refine and increase robustness of the model context protocol. These paper model context protocols can be connected to a chat agent 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 to interpret genomic variants and agents based on Scanpy and T ISSUE (transcript imputation with spatial single-cell uncertainty estimation) 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.

The research paper is the traditional unit of scientific communication. It remains the norm for documenting methods, results and insights, and is the primary way in which research is shared with the broader community. However, papers are fundamentally passive objects: a reader must discover the paper (not an easy task given the flood of publications), parse its contributions and manually determine how to apply them to their own work. In particular, when a paper describes a new computational method, substantial technical barriers often remain before the method can be used on new data. A reader might need to locate the corresponding code repository, install dependencies, configure environments and interpret the correct inputs and outputs. Even with well-maintained repositories, this process is often non-trivial.

For instance, consider AlphaGenome, which provides a powerful framework for genome-scale foundation modelling. Despite its utility, this system requires substantial technical expertise to set up and deploy, limiting accessibility for biologists who could otherwise benefit. Using AlphaGenome in code involves installing the environment, creating client objects with application programming interface keys, constructing inputs such as variant objects and selecting desired output modalities. Users must understand the application programming interface hierarchy and parameter semantics, which imposes a learning curve for biologists unfamiliar with these abstractions.

This illustrates a broader challenge: research outputs are passively siloed behind technical barriers. Paper2Agent reimagines research dissemination by turning static papers into active AI agents. Each agent serves as an interactive expert on the corresponding paper, capable of demonstrating, applying and adapting its methods to new projects.

AI agents are autonomous systems that can reason about tasks and act to achieve goals by leveraging external tools and resources. Modern AI agents are typically powered by large language models connected to external tools or applications programming interfaces, and can adapt based on feedback. Notably, because agents are built on top of large language models, users can interact with agents through human language, substantially reducing usage barriers for scientists. A range of recent systems, including general-purpose scientist agents and domain-specialized agents, have begun to demonstrate the potential of this paradigm, alongside efforts to automatically generate code from scientific text. Paper2Agent complements this emerging paradigm by generalizing the concept: any research paper can be converted into an agent that embodies the knowledge and methods described in the publication.

Article

Paper2Agent provides an automated workflow for converting a scientific paper into an agent. The core idea is to represent the paper as a model context protocol server. Model context protocol is a standardized protocol that allows structured applications programming interfaces and tools to be exposed in a way that is directly accessible to large language models and agent frameworks. The conversion process identifies a paper's key contributions, encapsulates them through a model context protocol server and links the server to large language model-based agents for natural language querying and autonomous execution. Users can then interact with the paper by asking questions, requesting demonstrations, or applying the method to new data. As an illustration, applying Paper2Agent to AlphaGenome would expose its genome foundation model as a model context protocol, so that instead of cloning repositories and configuring dependencies, a user could simply ask: 'Interpret the expected effect of this variant on chromatin accessibility in muscle cells'.

Earlier efforts have sought to make research outputs more executable and accessible, including executable papers, the Papers with Code initiative, containerized artefact platforms such as Binder and CodeOcean, and paper-to-code systems. Although these efforts improved reproducibility, substantial barriers remained for understanding, customizing and applying the code to new projects.

Paper2Agent substantially extends this trajectory by providing a new framework: a paper can be transformed into a capable agent that is accessible via natural language. In contrast to previous efforts, Paper2Agent shifts the research output from a document or codebase encoding knowledge to a knowledgeable entity capable of execution and dialogue. This extends beyond retrieval-augmented generation over paper text. Paper2Agent agentifies the full research outputs, including manuscripts, supplementary materials, code, datasets, executable examples and analysis workflows. In this framework, a paper becomes an executable research artefact that can answer questions, reproduce analyses, apply methods to new data and interoperate with other paper agents. This represents a new mode of scientific communication, moving beyond static dissemination to interactive collaboration.