Derong Xu

Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval

From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents

Attention Needs to Focus: A Unified Perspective on Attention Allocation

Memory Type Matters: Enhancing Long-Term Memory in Large Language Models with Hybrid Strategies

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning