DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval 事件

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval arXiv:2605.31377v1 Announce Type: cross Abstract: Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-horizon inference loops, leading to high inference cost and limited suitability for time-sensitive news retrieval. We propose DynaTree, a two-stage framework