LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos
Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must iteratively gather multiple discontinuous evidence clips. However, existing long-video benchmarks are lar
研究重點
Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must iteratively gather multiple discontinuous evidence clips. However, existing long-video benchmarks are lar
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
LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos ↗2026-11-05T00:00:00Z · 研究論文索引
延伸探索
相關研究
- Understand Once, Retrieve Many Times: SAADI for Single-Pass Retrieval of Distributed Evidence in Long Documents相同研究主題 · 2026-10-22
- Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models相同研究主題 · 2026-11-04
- Using iterative agentic retrieval-augmented generation to refine the risk of infection from social contexts during the COVID-19 pandemic: Development and Evaluation Study相同研究主題 · 2026-10-31