Morning Edition · Thursday, September 3, 2026Published at 2:26 AM EDT · New York

Two Papers Attack the Same Weakness in Retrieval Pipelines: Rewarding Right Answers From Wrong Steps

One trains a step-level reward model that judges retrieval quality independently of the final answer, the other teaches systems to decline when the retrieved evidence is insufficient.

Retrieval-augmented generation (RAG) grounds a model's answers in retrieved documents, and its persistent failure mode is that a multi-hop question can be answered correctly for the wrong reasons. Outcome-based training rewards the final an…