MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.

Authors

• Yiming Du The Chinese University of Hong Kong, Hong Kong, China
• Bingbing Wang Harbin Institute of Technology, Shenzhen, China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China
• Yang He
• Bin Liang Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong MoE Key Lab. of High Confidence Software Technologies(Hong Kong), China
• Baojun Wang Huawei Noah’s Ark Lab, Shenzhen, China
• Zhongyang Li Microsoft AI
• Lin Gui King's College London
• Jeff Z. Pan The University of Edinburgh
• Ruifeng Xu Harbin Institute of Technology, Shenzhen, China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China Peng Cheng Laboratory, Shenzhen, China
• Kam-Fai Wong Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong MoE Key Lab. of High Confidence Software Technologies(Hong Kong), China

Keywords

No keywords are indexed for this paper.