A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Researchers introduce APS-RAG, a hybrid retrieval system designed to manage complex institutional knowledge at the Advanced Photon Source.
- Combines dense, sparse, and knowledge-graph retrieval channels.
- Addresses the challenge of fragmented institutional knowledge in scientific settings.
- Introduces a new evaluation method grounded in real-world operations.
Scientific facilities like the Advanced Photon Source (APS) possess vast amounts of unstructured data, including electronic logbooks, maintenance records, and technical wikis. Traditional search methods often fail to capture the nuances of this specialized institutional knowledge.
To solve this, the researchers developed APS-RAG, a platform that utilizes a hybrid retrieval approach. This system combines dense and sparse retrieval with knowledge graphs to provide highly accurate, natural-language responses to staff queries.
Crucially, the study introduces an operations-grounded evaluation framework. This ensures that the AI's outputs are not just linguistically correct, but operationally sound and useful for the high-stakes environment of a scientific facility.
Demonstrates advanced hybrid RAG architectures using knowledge graphs.
Provides a case study on applying LLMs to highly specialized domains.
Shows how AI can manage complex, decades-old technical documentation.
- RAG
- Retrieval-Augmented Generation, a technique that provides LLMs with external data to improve accuracy.
- Knowledge Graph
- A structured representation of entities and their relationships used to improve data retrieval.
As Duke Health implements AI, oversight initiatives try to ensure ethical practices - The Duke Chronicle
Katy ISD sets new framework on artificial intelligence use in classrooms - ABC13 Houston
Artificial Intelligence Is Transforming Immigration Adjudications: What Every Employer and Applicant Needs to Know - WR Immigration
Adoption of artificial intelligence outpaces training in field epidemiology programs, new survey finds - CIDRAP
agentic artificial intelligence needs shared memory - SiliconANGLE
BusinessCursor makes its biggest India push yet ahead of SpaceX acquisition with localized pricing
AI code editor Cursor identifies India as its third-largest market and is launching localized pricing and expanded sales efforts there.
AI ToolsBeyond System Prompts: Enforcing Policy & Action Boundaries in Enterprise AI Agents
This article argues that system prompts are insufficient for controlling enterprise AI agents, proposing deterministic tool adapter validation, risk classification, and human-in-the-loop gates as more robust solutions.
SecurityI Tested 7 AI OSINT Agents on My Own Digital Footprint - Here's What They Found in 4 Minutes
A test of 7 AI OSINT agents revealed significant personal data in just 4 minutes. The agents were able to uncover information despite the tester's attempts at good opsec.
AI ToolsResurrecting the Panasonic WJ-MX50 in WebGPU
A developer has successfully ported a 1990s video mixer to WebGPU, showcasing the versatility of modern web technologies.
Microsoft unveils AI security tools it says outperform competing platforms
Microsoft has unveiled a suite of AI security tools that it claims outperform competing platforms, while also being more cost-effective.
AI ToolsNine Months of Nagging, Zero Reading
A GitHub Action has been developed to analyze nine months of AI commit history, revealing insights into AI's writing habits.