Bridging the Long-Term Gap: A Memory-Active Policy for Multi-Session Task-Oriented Dialogue

ACL ARR 2025 May Submission4301 Authors

Abstract: Existing Task-Oriented Dialogue (TOD) systems primarily focus on single-session dialogues, limiting their effectiveness in long-term memory augmentation. To address this challenge, we introduce a MS-TOD\footnote{Code and dataset will be released upon paper acceptance.} dataset, the first multi-session TOD dataset designed to retain long-term memory across sessions, enabling fewer turns and more efficient task completion. This defines a new benchmark task for evaluating long-term memory in multi-session TOD. Based on this new dataset, we propose a Memory-Active Policy (MAP) that improves multi-session dialogue efficiency through a two-stage approach. 1) Memory-Guided Dialogue Planning retrieves intent-aligned history, identifies key QA units via a memory judger, refines them by removing redundant questions, and generates responses based on the reconstructed memory. 2) Proactive Response Strategy detects and correct errors or omissions, ensuring efficient and accurate task completion. We evaluate MAP on MS-TOD dataset, focusing on response quality and effectiveness of the proactive strategy. Experiments on MS-TOD demonstrate that MAP significantly improves task success and turn efficiency in multi-session scenarios, while maintaining competitive performance on conventional single-session tasks.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: long-term memory, task-oriented dialogue, multi-session dialogue

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 4301