arXiv:2606. 18381v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that existing methods address through LLM-guided chunking, single-level context expansion, or hierarchical summarization.
Paper
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
Unreadunread