Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
It addresses the need for efficient and reliable tools to accelerate scientific discovery for researchers, but is incremental as it synthesizes existing work.
This survey tackles the growing complexity of scientific research by reviewing LLM-based scientific agents that automate tasks like hypothesis generation and data analysis, highlighting their specialized architectures and applications across fields.
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.