Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

TL;DR

Paper2Agent reimagines scientific communication by transforming static publications into active AI agents through Model Context Protocol servers. It automates extraction of methods, datasets, and workflows, wraps them as reusable MCP tools, and connects them to chat agents for natural-language querying and autonomous execution. Case studies on AlphaGenome, TISSUE, and Scanpy demonstrate reliable reproduction, efficiency gains, and the ability to collaborate across papers via AI co-scientists, accelerating discovery. This framework lowers adoption barriers, enhances reproducibility, and lays groundwork for an ecosystem of AI-enabled co-scientists.

Abstract

We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. Paper2Agent automatically created AI co-scientist that identified new splicing variant associated with ADHD risk. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.

Figures (6)

• Figure 1: Overview of the Paper2Agent. (A) Paper2Agent turns research papers into interactive AI agents by building remote MCP servers with tools, resources, and prompts. Connecting an AI agent to the server creates a paper-specific agent for diverse tasks. (B) Workflow of Paper2Agent. It starts with codebase extraction and automated environment setup for reproducibility. Core analytical features are wrapped as MCP tools, then validated through iterative testing. The resulting MCP server is deployed remotely and integrated with an AI agent, enabling natural-language interaction with the paper’s methods and analyses.
• Figure 2: Overview of the Paper2Agent-generated AlphaGenome agent. (A) Construction of the AlphaGenome MCP server and agent. (B) Benchmarking the AlphaGenome agent on tutorial-based and novel queries shows 100% accuracy, above that achieved by the general agents Claude with the AlphaGenome codebase (Claude + Repo) or Biomni. (C) The AlphaGenome agent also shows improved computational efficiency in terms of reduced run-time for each query compared to Claude + Repo and Biomni agents. (D) Automated planning and interpretation of GWAS loci through iterative planning–action–observation cycles by the AlphaGenome agent.
• Figure 3: Overview of the Paper2Agent-generated TISSUE agent. (A) Construction of the TISSUE MCP server and agent. (B) Q&A support for uncertainty-aware spatial transcriptomics analysis. (C) Reproducibility confirmed by matching human researcher results. (D) Structured MCP resources enable standardized dataset access and automated downloads.
• Figure 4: Overview of the Paper2Agent-generated Scanpy agent. (A) Construction of the Scanpy MCP server and agent. (B) MCP prompts encode a standardized single-cell preprocessing and clustering pipeline. (C) Agent reproduces human researcher results, requiring only the dataset path as input.
• Figure 5: Paper2Agent enables autonomous AI-driven collaboration and genomic discovery. (A) Paper2Agent transforms scientific papers into Model Context Protocol (MCP) resources for both methods and data, allowing AI co-scientist to integrate them and autonomously generate novel hypotheses and actionable research plans. (B) Using the ADHD GWAS dataset and the AlphaGenome method MCPs, the agent autonomously generates and tests scientific hypotheses, identifies causal variants, and interprets molecular mechanisms. The agent identified rs1626703 as a likely causal variant among 209 candidate variants. The agent then showed computationally using AlphaGenome that rs1626703 alters splicing of MPHOSPH9 and increases its expression in glutamatergic neurons, revealing a plausible causal mechanism for ADHD risk.