mlsanityData to 7 Oct 2026

SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications

arXiv 2604.13180 ↗First posted 14 Apr 2026cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 27 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

17 of 27 references.

References · 17

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  8. 2022PAL: Program-aided Language Modelscited by 635
  9. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  10. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  11. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  12. 2017Classification without labels: Learning from mixed samples in high energy physicscited by 42
5 more
  1. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30
  2. 2024Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulationcited by 15
  3. 2024HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAscited by 9
  4. 2025Snakemaker: Seamlessly transforming ad-hoc analyses into sustainable Snakemake workflows with generative AIcited by 3
  5. 2025Edge Machine Learning for Cluster Counting in Next-Generation Drift Chamberscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
  2. 2026Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
  3. 2026Experiments in Agentic AI for Science
  4. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
  5. 2025Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
  6. 2025State and Memory is All You Need for Robust and Reliable AI Agents
  7. 2025The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
  8. 2026Atria Dawn: The Dawn of Agentic Superintelligence