Megadose AI progress, ranked and analyzed.

A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility

· ArXiv · AI/CL/LG ·
APS-RAG is already deployed for staff at the Advanced Photon Source and beat a BM25 baseline on an operations QA benchmark.

The system combines dense, sparse, and knowledge-graph retrieval, then adds a corrective agent loop and ReAct tooling over MCP. The authors built APS-Bench, a 50-question dataset with auditable gold answers, to test answers against facility operations knowledge. The full corrective Agentic GraphRAG reached 70.3% strict vital-nugget recall, compared with 63.8% for naive BM25. Removing the cross-encoder reranker sharply hurt recall, while the graph channel and corrective loop helped only marginally. ArXiv · AI/CL/LG's note

score 4

Categories: Research