3 papers
cs.CL2026
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Pengyu Wang, Benfeng Xu, Shaohan Wang +5
Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph-based indexing, and agentic search, but these paradigms are usually evaluated on different benchmarks…
cs.CL2026
A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
Mingxuan Du, Benfeng Xu, Chiwei Zhu +4
Frontier language models have demonstrated strong reasoning and long-horizon tool-use capabilities. However, existing RAG systems fail to leverage these capabilities. They still re…
cs.CL2026
WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora
Pengyu Wang, Benfeng Xu, Licheng Zhang +4
Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scattered evidence acros…