SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

TL;DR

SciAgents is an AI framework that combines large knowledge graphs, language models, and multi-agent systems to autonomously explore scientific data, uncover hidden relationships, and accelerate materials discovery.

Contribution

The paper introduces SciAgents, a novel multi-agent system integrating ontological knowledge graphs and LLMs for autonomous scientific hypothesis generation and discovery.

Findings

Revealed hidden interdisciplinary relationships in materials science

Achieved scalable, precise, and exploratory scientific analysis

Enabled autonomous hypothesis refinement and material discovery

Abstract

A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to biologically inspired materials, SciAgents reveals hidden interdisciplinary relationships that were previously considered unrelated, achieving a scale, precision, and exploratory power that surpasses traditional human-driven research methods. The framework autonomously generates and refines research hypotheses, elucidating underlying mechanisms, design principles, and unexpected material properties. By integrating these capabilities in a modular fashion, the intelligent system yields material discoveries, critique and improve existing hypotheses, retrieve up-to-date data about existing research, and highlights their strengths and limitations. Our case studies demonstrate scalable capabilities to combine generative AI, ontological representations, and multi-agent modeling, harnessing a `swarm of intelligence' similar to biological systems. This provides new avenues for materials discovery and accelerates the development of advanced materials by unlocking Nature's design principles.