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 are primarily based on semantic similarity, overlooking task intent and reducing task coherence in multisession dialogues. To address this challenge, we introduce MemGuide, a two-stage framework for intent-driven memory selection. (1) Intent-Aligned Retrieval matches the current dialogue context with stored intent descriptions in the memory bank, retrieving QA-formatted memory units that share the same goal. (2) Missing-Slot Guided Filtering employs a chain-of-thought slot reasoner to enumerate unfilled slots, then uses a fine-tuned LLaMA-8B filter to re-rank the retrieved units by marginal slot-completion gain. The resulting memory units inform a proactive strategy that minimizes conversational turns by directly addressing information gaps. Based on this framework, we introduce the MS-TOD 1 , the first multi-session TOD benchmark comprising 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets, supporting efficient multi-session task completion. Evaluations on MS-TOD show that MemGuide raises the task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns in multi-session settings, and maintains parity with single-session benchmarks. * These authors contributed equally. 1 Code and dataset will be released upon paper acceptance. Domain: Travel Intent: BookHotel User: Hi. Did you find any good hotel options for my stay in San Francisco? Assistant: Hi! Yes, I did. The first option is Hotel ABC, which offers free breakfast and Wi-Fi. The second option is Hotel XYZ, located near popular tourist spots and includes a gym facility. Which one sounds better to you. User: Hotel XYZ sounds better.