MemGuide：面向目标的多会话LLM智能体的意图驱动记忆选择
MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
AI总结：
针对多会话TOD系统因语义相似度忽略任务意图导致连贯性下降的问题，提出两阶段意图驱动记忆选择框架MemGuide，通过意图对齐检索和缺失槽位引导过滤优化记忆利用，并构建首个多会话TOD基准MS-TOD，使任务成功率提升11%且对话长度减少2.84轮。
摘要：
现代面向任务的对话（TOD）系统越来越依赖大语言模型（LLM）智能体，利用检索增强生成（RAG）和长上下文能力来实现长期记忆利用。然而，这些方法主要基于语义相似度，忽略了任务意图，降低了多会话对话中的任务连贯性。为了解决这一挑战，我们引入了MemGuide，一个用于意图驱动记忆选择的两阶段框架。（1）意图对齐检索将当前对话上下文与记忆库中存储的意图描述进行匹配，检索出共享相同目标的QA格式记忆单元。（2）缺失槽位引导过滤采用思维链槽位推理器枚举未填充的槽位，然后使用微调的LLaMA-8B过滤器通过边际槽位完成增益对检索单元进行重排序。生成的记忆单元为一种主动策略提供信息，该策略通过直接解决信息缺口来最小化对话轮次。基于此框架，我们引入了MS-TOD，这是第一个多会话TOD基准，包含132个多样化角色、956个任务目标以及标注的意图对齐记忆目标，支持高效的多会话任务完成。在MS-TOD上的评估表明，MemGuide在多会话设置下将任务成功率提高了11%（88% -> 99%），并将对话长度减少了2.84轮，同时与单会话基准保持同等水平。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
