mlsanityData to 7 Oct 2026

Experiments in Agentic AI for Science

arXiv 2605.26305 ↗First posted 25 May 2026cs.AI cs.SY eess.SYcited by 0

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

Abstract (arXiv)

This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote Brain architecture via Google Colab, utilizing Python-based local orchestrators to invoke large language model (LLM) cloud backends. The first agent, DeepTS/DeepCollector, automates the large-scale curation, extraction, and deduplication of time-series datasets. The second, DeepScribe, is an autonomous presentation analyzer that converts visually dense, mathematically complex physics lectures into structured scientific reports. Through practical systems engineering-such as granular attribute extraction (Cellular RAG), remote data inspection, and distributed concurrency controls-we demonstrate how agentic AI can overcome the context and reasoning limitations of current state-of-the-art systems to rigorously support scientific workflows. Finally, we outline a generalization of DeepTS to support deep knowledge graphs and discuss the application of this conceptual approach to high-energy physics (DeepQCD).

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 36 of its 100 references that are in the map. First posted on arXiv 25 May 2026.

Builds on

36 of 100 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft27 Apr
  2. 2026AI Agents Can Already Autonomously Perform Experimental High Energy Physics20 Mar
  3. 2026Embodied Science: Closing the Discovery Loop with Agentic Embodied AI20 Mar
  4. 2025SR-Scientist: Scientific Equation Discovery With Agentic AI13 Oct
  5. 2025Universal Deep Research: Bring Your Own Model and Strategy29 Aug
  6. 2025URSA: The Universal Research and Scientific Agent27 Jun
  7. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun

Other references · 29

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2024GPT-4o System Cardcited by 4,467
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  11. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  12. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
17 more
  1. 2019How Can We Know What Language Models Know?cited by 953
  2. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  3. 2014OpenML: networked science in machine learningcited by 523
  4. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  5. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 168
  6. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 151
  7. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 150
  8. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  9. 2021hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devicescited by 61
  10. 2025Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmapcited by 19
  11. 2025Procedural Knowledge Improves Agentic LLM Workflowscited by 7
  12. 2025InferA: A Smart Assistant for Cosmological Ensemble Datacited by 6
  13. 2025EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistantscited by 5
  14. 2023TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecastingcited by 4
  15. 2025Efficient Model Selection for Time Series Forecasting via LLMscited by 4
  16. 2026Wattchmen: Watching the Wattchers -- High Fidelity, Flexible GPU Energy Modelingcited by 3
  17. 2025An MLCommons Scientific Benchmarks Ontologycited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications
  2. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
  3. 2025Deep Research Agents: A Systematic Examination And Roadmap
  4. 2025Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
  5. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
  6. 2025The AI Cosmologist I: An Agentic System for Automated Data Analysis
  7. 2025Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
  8. 2026A Cloud-based Multi-Agentic Workflow for Science