Zhubo Shi
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.
This paper introduces DynaKRAG, a method for multi-hop retrieval-augmented generation that learns a shared policy for evidence operations, achieving state-of-the-art results on three benchmarks.
Papers
DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
Yaqi Wu, Xiaolei Guo, Chenyu Zhou, Jiaqi Huang +6 more
This paper introduces DynaKRAG, a method for multi-hop retrieval-augmented generation that learns a shared policy for evidence operations, achieving state-of-the-art results on three benchmarks.