PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts Paper • 2508.09848 • Published Aug 13 • 67
Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings Paper • 2506.08592 • Published Jun 10 • 22
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning Paper • 2508.10419 • Published Aug 14 • 74
