Saved in:
Bibliographic Details
Main Authors: Fox, Judy, Fox, Geoffrey
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26305
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916067644801024
author Fox, Judy
Fox, Geoffrey
author_facet Fox, Judy
Fox, Geoffrey
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2605_26305
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Experiments in Agentic AI for Science
Fox, Judy
Fox, Geoffrey
Artificial Intelligence
Systems and Control
High Energy Physics - Phenomenology
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).
title Experiments in Agentic AI for Science
topic Artificial Intelligence
Systems and Control
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2605.26305