All news
2 articles- paperPVLDB·25 Oct 20265.2Evergreen checks claims in LLM-written summaries of tables by compiling each claim into a semantic verification query with citations. It keeps F1 at 0.94 while cutting cost 3.1x through early stopping, relevance sorting and prompt caching.
- paperPVLDB·25 Oct 20264.9NOMA treats multi-agent LLM pipelines as a query optimization problem, jointly choosing topology, model and execution engine against latency, cost and accuracy instead of hand-wiring fixed agent graphs.