SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications
For researchers, it offers a practical tool to offload routine scientific tasks, but the approach is incremental, building on existing agentic AI concepts.
The paper presents SciFi, a safe, lightweight, and user-friendly agentic AI framework for autonomous execution of well-defined scientific tasks, combining an isolated execution environment, a three-layer agent loop, and a self-assessing do-until mechanism to ensure reliable operation with minimal human intervention.
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe, lightweight, and user-friendly agentic framework for the autonomous execution of well-defined scientific tasks. The framework combines an isolated execution environment, a three-layer agent loop, and a self-assessing do-until mechanism to ensure safe and reliable operation while effectively leveraging large language models of varying capability levels. By focusing on structured tasks with clearly defined context and stopping criteria, the framework supports end-to-end automation with minimal human intervention, enabling researchers to offload routine workloads and devote more effort to creative activities and open-ended scientific inquiry.