Experiments in Agentic AI for Science
Quick Answer
This paper introduces two frameworks for agentic AI in scientific workflows: DeepTS/DeepCollector for time-series data curation and DeepScribe for converting complex physics lectures into structured reports.
Quick Take
Utilizing a hybrid Local Body, Remote Brain architecture via Google Colab, these systems enhance scientific workflows by addressing context and reasoning limitations of current AI models.
Key Points
- DeepTS/DeepCollector automates curation and deduplication of time-series datasets.
- DeepScribe converts complex physics lectures into structured scientific reports.
- Systems use Python-based local orchestrators with cloud backends.
- Agentic AI frameworks improve scientific workflows by enhancing reasoning capabilities.
- DeepTS generalization supports deep knowledge graphs, applicable in high-energy physics.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2605. 26305v1 Announce Type: new 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 (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 ), 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).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.