The Hitchhiker's Guide to Autonomous Research: A Survey of Scientific Agents.
TL;DR
This survey bridges the existing gap by presenting a comprehensive blueprint for scientific agents' design and introduces a unified taxonomy based on capability envelope and capability maturity, characterizing both the scope of scientific workflow coverage and the reliability of agent behavior under realistic research conditions.
Abstract
The advancement of LLM-based agents is redefining AI for Science (AI4S) by enabling autonomous scientific research. Prominent LLMs exhibited expertise across multiple domains, catalysing constructions of domain-specialised scientific agents. Nevertheless, the profound epistemic and methodological gaps between AI and the natural sciences still impede the systematic design, training, and validation of these agents. This survey bridges the existing gap by presenting a comprehensive blueprint for scientific agents' design. It first clarifies the concept of scientific agents and distinguishes them from general-purpose agents in terms of their goal orientation, workflow embedding, and scientific commitments. It then introduces a unified taxonomy based on capability envelope and capability maturity, characterizing both the scope of scientific workflow coverage and the reliability of agent behavior under realistic research conditions. Building on this taxonomy, the survey further connects scientific agent design with the research life cycle by reviewing construction strategies, capability enhancement methods, evaluation paradigms, and future challenges. This unified perspective aims to provide practical guidance for designing domain-specific scientific agents and to promote the convergence of AI research and natural scientific discovery. To support long-term progress, we curate a live repository (AWESOME_SCIENTIFIC_AGENT) that continuously aggregates emerging methods, benchmarks, and best practices.