Agents
SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications
arXiv:2604.13180v1 Announce Type: new Abstract: Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliab
arXiv:2604.13180v1 Announce Type: new Abstract: 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.
Related
- MIND: AI Co-Scientist for Material Research
- Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models
- From Helpful to Trustworthy: LLM Agents for Pair Programming
- Sanity Checks for Agentic Data Science
Source: arXiv cs.AI | 2026-04-17