3 papers
cs.CL2026
Credible Plan-Driven RAG Method for Multi-Hop Question Answering
Ningning Zhang, Chi Zhang, Zhizhong Tan +3
Retrieval-augmented generation (RAG) has demonstrated strong performance in single-hop question answering (QA) by integrating external knowledge into large language models (LLMs).…
cs.AI2026
HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
Ningning Zhang, Xingxing Yang, Zhizhong Tan +2
Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under contin…
cs.LG2025
FedGRec: Dynamic Spatio-Temporal Federated Graph Learning for Secure and Efficient Cross-Border Recommendations
Zhizhong Tan, Jiexin Zheng, Xingxing Yang +3
Due to the highly sensitive nature of certain data in cross-border sharing, collaborative cross-border recommendations and data sharing are often subject to stringent privacy prote…