4 papers
RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation
Linyao Zheng, Xuhang Shi, Zhifang Mao +2
Iterative retrieval-augmented generation (RAG) accumulates knowledge from retrieved evidence to answer complex questions, but existing methods struggle to reconstruct entity corres…
EvLink: Source-Grounded Evidence Linking for Graph RAG
Linyao Zheng, Xuhang Shi, Zhifang Mao +3
Graph-based Retrieval-Augmented Generation (GraphRAG) supports multi-hop reasoning by organizing corpora into structured graphs. However, graph reachability often captures semantic…
LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding
Linyao Zheng, Xuhang Shi, Zhifang Mao +4
Graph-based Retrieval-Augmented Generation (GraphRAG) retrieves evidence for multi-hop questions over structured cor- pus graphs. Existing GraphRAG methods leave the connection bet…
HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS
Zhifang Mao, Linyao Zheng, Xuhang Shi +1
LLM-based multi-agent systems (MAS) typically optimize a single topology, restricting reasoning to a narrow trajectory and limiting comprehensive analytical capacity. Naively mergi…