Towards an AI co-scientist

2025-02-26

AI Summary

Low efficiency in scientific hypothesis generation hampers biomedical discovery. Method: We propose an asynchronous multi-agent AI system powered by Gemini 2.0, introducing the novel “generate–debate–evolve” collaborative paradigm and a tournament-based hypothesis evolution mechanism, enabling test-time computation-driven hypothesis self-optimization. Our approach integrates multi-agent architecture, test-time scaling, and domain-specific knowledge constraints to support diverse tasks—including drug repurposing (e.g., AML in vitro tumor suppression), novel target identification (epigenetic targets for liver fibrosis, validated via organ-on-a-chip), and bacterial antimicrobial resistance mechanism analysis. Contribution/Results: This work presents the first systematic validation of AI-driven hypothesis discovery in biomedicine. Multiple original hypotheses were experimentally confirmed; several align closely with unpublished experimental data. The framework establishes a reproducible, empirically verifiable paradigm for AI-augmented scientific discovery.

Technology Category

• Multiagent Systems: Adversarial Agents
• Search and Optimization: Metareasoning and Metaheuristics
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To augment this process, we introduce an AI co-scientist, a multi-agent system built on Gemini 2.0. The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and aligned to scientist-provided research objectives and guidance. The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method and accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute, improving hypothesis quality. While general purpose, we focus development and validation in three biomedical areas: drug repurposing, novel target discovery, and explaining mechanisms of bacterial evolution and anti-microbial resistance. For drug repurposing, the system proposes candidates with promising validation findings, including candidates for acute myeloid leukemia that show tumor inhibition in vitro at clinically applicable concentrations. For novel target discovery, the AI co-scientist proposed new epigenetic targets for liver fibrosis, validated by anti-fibrotic activity and liver cell regeneration in human hepatic organoids. Finally, the AI co-scientist recapitulated unpublished experimental results via a parallel in silico discovery of a novel gene transfer mechanism in bacterial evolution. These results, detailed in separate, co-timed reports, demonstrate the potential to augment biomedical and scientific discovery and usher an era of AI empowered scientists.

Problem

• AI co-scientist aids scientific hypothesis generation.
• Multi-agent system enhances biomedical research discovery.
• Automated process improves drug target identification.

Innovation

• Multi-agent system for hypothesis generation
• Asynchronous task execution framework
• Tournament evolution process for self-improvement