{"slug": "experiments-in-agentic-ai-for-science", "title": "Experiments in Agentic AI for Science", "summary": "Researchers have developed two new frameworks for autonomous, agentic AI in scientific workflows, both using a hybrid Local Body, Remote Brain architecture via Google Colab. The first system, DeepTS/DeepCollector, automates large-scale curation and deduplication of time-series datasets, while the second, DeepScribe, converts complex physics lectures into structured scientific reports. These systems demonstrate how agentic AI can overcome current limitations in context and reasoning to rigorously support scientific research.", "body_md": "arXiv:2605.26305v1 Announce Type: new\nAbstract: 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).", "url": "https://wpnews.pro/news/experiments-in-agentic-ai-for-science", "canonical_source": "https://arxiv.org/abs/2605.26305", "published_at": "2026-05-27 04:00:00+00:00", "updated_at": "2026-05-27 04:31:31.537287+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "large-language-models", "ai-research"], "entities": ["Google Colab", "DeepTS", "DeepCollector", "DeepScribe", "Cellular RAG", "DeepQCD"], "alternates": {"html": "https://wpnews.pro/news/experiments-in-agentic-ai-for-science", "markdown": "https://wpnews.pro/news/experiments-in-agentic-ai-for-science.md", "text": "https://wpnews.pro/news/experiments-in-agentic-ai-for-science.txt", "jsonld": "https://wpnews.pro/news/experiments-in-agentic-ai-for-science.jsonld"}}