Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909734856032256 |
|---|---|
| author | Du, Yiming Wang, Bingbing He, Yang Liang, Bin Wang, Baojun Li, Zhongyang Gui, Lin Pan, Jeff Z. Xu, Ruifeng Wong, Kam-Fai |
| author_facet | Du, Yiming Wang, Bingbing He, Yang Liang, Bin Wang, Baojun Li, Zhongyang Gui, Lin Pan, Jeff Z. Xu, Ruifeng Wong, Kam-Fai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents Du, Yiming Wang, Bingbing He, Yang Liang, Bin Wang, Baojun Li, Zhongyang Gui, Lin Pan, Jeff Z. Xu, Ruifeng Wong, Kam-Fai Computation and Language 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. |
| title | MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.20231 |