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

TL;DR

MemGuide is a novel framework that improves multi-session goal-oriented dialogue systems by using intent-driven memory retrieval and filtering, significantly enhancing task success and efficiency.

Contribution

It introduces MemGuide, a two-stage intent-driven memory selection framework, and the MS-TOD benchmark for evaluating multi-session task-oriented dialogues.

Findings

Task success rate increased by 11% using MemGuide.

Dialogue length reduced by 2.84 turns with MemGuide.

Maintains performance parity with single-session benchmarks.

Abstract

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 multi-session 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, 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, while maintaining parity with single-session benchmarks.