Autonomous Research Assistants for Hybrid Intelligence: Landscape and Challenges

Abstract

We present an overview of AI-based tools assisting the research process, analyzing them from the point of view of Hybrid (human-AI) Intelligence (HI). While Autonomous Research Assistants (RAs) are gaining new interest by the latest advancements in AI (cf. Large Language Models), limitations arise when deployed in real-world use-cases. Starting from the hypothesis that principles from the emerging field of HI could enhance the synergy between researchers and AI tools, we explore what requirements allow to create HI RAs, using a survey of existing systems. We performed a review of 47 relevant articles published in the last 10 years, and we analyzed them according to various capabilities and characteristics proposed in the Hybrid Intelligence literature. Finally, we identify which future research lines could be followed to develop assistive systems that better combine the capabilities of humans and artificial RAs in a synergistic way.