打造安全轻量的科学任务自动化框架，让研究者少跑腿多创新。
SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications
- 三重结构循环+隔离环境，保障自主执行安全可靠
- 支持明确任务与终止条件，实现端到端自动运行
- 适合科研人员自动化常规工作，专注创造性探索
近期智能体人工智能的发展推动了日益自主的工作流程，但现有系统在真实科研场景中部署仍面临诸多挑战。本文提出一种安全、轻量、用户友好的智能体框架，用于自主执行明确的科学任务。该框架结合隔离执行环境、三层智能体循环和自评估直到机制，确保安全可靠运行，同时有效利用不同能力水平的大语言模型。通过聚焦具有清晰上下文和终止条件的结构化任务，框架实现端到端自动化，仅需最少人工干预，使研究人员可将日常负担转移，更专注于创造性活动与开放性科学探究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。