Experiments in Agentic AI for Science
Summary
This paper presents two agentic AI frameworks, DeepTS/DeepCollector and DeepScribe, that automate scientific workflows including time-series data curation and conversion of physics lectures into structured reports, using a hybrid local-cloud architecture with LLMs.
View Cached Full Text
Cached at: 05/27/26, 09:03 AM
# Experiments in Agentic AI for Science Source: [https://arxiv.org/abs/2605.26305](https://arxiv.org/abs/2605.26305) [View PDF](https://arxiv.org/pdf/2605.26305) > Abstract: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 \(DeepQCD\)\. ## Submission history From: Geoffrey Fox \[[view email](https://arxiv.org/show-email/85017892/2605.26305)\] **\[v1\]**Mon, 25 May 2026 19:57:57 UTC \(1,028 KB\)
Similar Articles
Most “agentic AI” conversations feel too abstract. Here is how my agentic research system looks like
The author shares a practical breakdown of an agentic research system they built to identify and evaluate AI use cases within companies. The system uses six agents for discovery, evaluation, and context extraction, emphasizing human-in-the-loop decision-making over full autonomy.
Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse
This paper benchmarks agentic AI systems on the task of loading, understanding, and reformatting fragmented neuroscience data, finding that while agents perform well on subtasks, they rarely achieve fully error-free end-to-end solutions and human oversight remains necessary.
@dair_ai: https://x.com/dair_ai/status/2061104052818108476
A roundup of three notable AI papers: SkillOpt treats skill documents as trainable parameters to optimize frozen agents; a new method compiles agentic workflows into model weights for 100x cost reduction; and AutoScientists introduces a decentralized agent team for long-running science without a central planner.
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
AutoSci is a memory-centric agentic system designed to automate the full scientific research lifecycle, from literature understanding to rebuttal, using LLM-based agents with persistent memory and self-evolution capabilities.
Position: Agentic AI System Is a Foreseeable Pathway to AGI
This paper argues that monolithic scaling of a single model is insufficient for achieving AGI and proposes Agentic AI with multi-agent collaboration as a necessary paradigm, demonstrating theoretically that agentic systems achieve exponentially superior generalization and sample efficiency.