Understand Once, Retrieve Many Times: SAADI for Single-Pass Retrieval of Distributed Evidence in Long Documents
Long-document retrieval is challenging when relevant evidence is distributed across distant passages or requires multiple reasoning hops, especially under a limited retrieval budget. Single-pass top-k retrievers offer predictable query-time computation and latency, whereas agentic systems seek higher recall by reading
研究重點
Long-document retrieval is challenging when relevant evidence is distributed across distant passages or requires multiple reasoning hops, especially under a limited retrieval budget. Single-pass top-k retrievers offer predictable query-time computation and latency, whereas agentic systems seek higher recall by reading
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
Understand Once, Retrieve Many Times: SAADI for Single-Pass Retrieval of Distributed Evidence in Long Documents ↗2026-10-20T00:00:00Z · 研究論文索引
延伸探索
相關研究
- LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos相同研究主題 · 2026-11-07
- Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models相同研究主題 · 2026-11-04
- Curriculum-aligned analysis of assessment feedback: a retrieval-augmented large language model approach for revealing fine-grained student error patterns in higher educat相同研究主題 · 2026-11-17