SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation

ArXi:2603.08329v1 Announce Type: new Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while long-context large language models (LLMs) struggle to reason reliably over massive inputs. We