Dans l'actualité
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
arXiv cs.AI · Publié le · 3 min de lecture
En 30 secondes
- Ce qui s'est passé
- Researchers deployed APS-RAG, a retrieval-augmented generation system combining dense, sparse, and knowledge-graph search channels with a corrective agentic loop for querying scientific facility operational knowledge.
- Pourquoi ça compte
- Matters for engineers at large research facilities who need to search decades of accumulated operational data including logbooks, maintenance records, and control-system information through natural language.
- Vigilance
- Performance gains from graph channels and corrective loops were marginal; cross-encoder reranking proved critical, and the system was evaluated on only fifty questions specific to one facility.
Écouter ce résumé
Extrait de l'article
-->
Physics > Accelerator Physics
arXiv:2607.24663v1 (physics)
[Submitted on 27 Jul 2026]
Title: A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Authors: Rajat Sainju , Dariusz Jarosz , Hairong Shang , Michael Prince , Ryan M. Aydelott , Mathew J. Cherukara , Yine Sun , Michael D. Borland
View a PDF of the paper titled A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility, by Rajat Sainju and 7 other authors
View PDF HTML (experimental)
Abstract: Scientific user facilities accumulate decades of operational knowledge that no single search index covers: electronic logbooks, technical documents, internal wikis, operations chat messages, maintenance records, and live control-system data. We present APS-RAG, Advanced Photon Source Retrieval Augmented Generation, a deployed platform that makes the institutional knowledge at the Advanced Photon Source (APS) accessible to staff through natural-language queries, along with an operations-grounded evaluation. The retrieval engine fuses dense, sparse, and knowledge-graph (KG) channels with query-type-adaptive reciprocal-rank fusion, adds a corrective agentic loop, and runs a native-tool ReAct executor over a Model Context Protocol (MCP) tooling layer. We construct APS-Bench, a 50-question, question-answering (QA) dataset with auditable gold an
Extrait de l'original. Lisez l'article complet à la source.
- agent
- agentic
- rag
- retrieval
The Agent Architect
Un pattern, un compromis, une panne de production racontée. Un brief hebdomadaire court pour ceux qui construisent des systèmes agentiques.
Un email par semaine, désinscription en un clic. Votre adresse ne sert qu'à envoyer le brief.