Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents

TL;DR

This survey reviews the development, architecture, and applications of LLM-based scientific agents, emphasizing their role in automating complex scientific tasks, integrating domain knowledge, and accelerating research breakthroughs.

Contribution

It provides a comprehensive overview of specialized LLM-based scientific agents, highlighting their unique features, challenges, and potential to transform scientific research.

Findings

LLM-based scientific agents integrate domain knowledge and tools.

They improve reproducibility and handle complex data types.

They face ethical and validation challenges.

Abstract

As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large language models (LLMs) are now evolving into LLM-based scientific agents that automate critical tasks ranging from hypothesis generation and experiment design to data analysis and simulation. Unlike general-purpose LLMs, these specialized agents integrate domain-specific knowledge, advanced tool sets, and robust validation mechanisms, enabling them to handle complex data types, ensure reproducibility, and drive scientific breakthroughs. This survey provides a focused review of the architectures, design, benchmarks, applications, and ethical considerations surrounding LLM-based scientific agents. We highlight why they differ from general agents and the ways in which they advance research across various scientific fields. By examining their development and challenges, this survey offers a comprehensive roadmap for researchers and practitioners to harness these agents for more efficient, reliable, and ethically sound scientific discovery.