Tao Duan

Right Family, Wrong Skill: Benchmarking Risk Exposure in Agent Skill Retrieval

MCoRe: Multi-Entry Complementary Retrieval with Reflection-Guided Iteration for Multi-Hop QA

MCoRe, a multi-entry complementary retrieval framework with reflection-guided iteration for multi-hop QA that enables multi-entry complementary retrieval by indexing entry units at multiple semantic resolutions with explicit links to chunk evidence, and fusing cross-resolution hits via chunk-level voting to form a comp...

MCoRe: Multi-Entry Complementary Retrieval with Reflection-Guided Iteration for Multi-Hop QA

Retrieval-augmented generation (RAG) has become a standard paradigm for knowledge-intensive question answering by grounding large language models (LLMs) in external evidence. However, open-domain multi-hop question answering (QA) remains challenging for two reasons. First, evidence dispersion across documents and non-c...