EMIR$^2$：演化感知记忆与意图引导的多轮检索
EMIR$^2$: Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval
浏览论文内容
中文总结 AI 辅助
针对LLM智能体长期记忆难以跟踪事实变化和整合分布式证据的问题，提出演化感知记忆框架EMIR$^2$，通过状态演化记忆图和意图引导的多轮检索，在LoCoMo和MemConflict上实现超12%的相对性能提升。
中文摘要 AI 辅助
长期记忆使大型语言模型（LLM）智能体能够利用历史交互来执行未来任务。然而，现有的记忆系统难以利用持续演化的历史信息，因为它们通常依赖静态记忆表示和单轮检索策略，无法跟踪事实变化或整合长期交互中的分布式证据。为解决这些挑战，我们提出了\ extsc{EMIR}$^{2}$，一个具有意图引导的多轮检索的\ extbf{演化感知}记忆框架，使LLM智能体能够维护不断演化的历史知识并自适应地检索相关证据。具体而言，\ extsc{EMIR}$^{2}$构建了状态演化记忆图（SEMG），将长期记忆表示为由时间事件轨迹和证据关联支持的演化知识状态。通过基于证据的更新维护语义状态，SEMG保留了历史演化，并能在复杂和冲突场景下实现证据追踪。在此基础上，我们引入了一种意图引导的多轮检索机制，该机制迭代地识别缺失证据，并根据累积信息扩展检索。在LoCoMo和MemConflict上的实验表明，\ extsc{EMIR}$^{2}$改善了长期记忆利用、动态和静态冲突处理以及复杂检索性能，在特定类别中实现了超过12%的相对提升。这些结果凸显了联合建模记忆演化和自适应证据获取对长期智能体交互的有效性。
英文摘要
Long-term memory enables large language model (LLM) agents to leverage historical interactions for future tasks. However, existing memory systems struggle to utilize continuously evolving historical information, as they often rely on static memory representations and single-round retrieval strategies, failing to track factual changes or integrate distributed evidence across long-term interactions. To address these challenges, we propose \textsc{EMIR}$^{2}$, an \textbf{E}volution-Aware \textbf{M}emory framework with \textbf{I}ntent-Guided Multi-\textbf{R}ound \textbf{R}etrieval, enabling LLM agents to maintain evolving historical knowledge and adaptively retrieve relevant evidence. Specifically, \textsc{EMIR}$^{2}$ constructs a State-Evolving Memory Graph (SEMG) that represents long-term memory as evolving knowledge states supported by temporal event trajectories and evidential associations. By maintaining semantic states through evidence-based updates, SEMG preserves historical evolution and enables evidence tracing under complex and conflicting scenarios. Building upon this, we introduce an intent-guided multi-round retrieval mechanism that iteratively identifies missing evidence and expands retrieval based on accumulated information. Experiments on LoCoMo and MemConflict demonstrate that \textsc{EMIR}$^{2}$ improves long-term memory utilization, dynamic and static conflict handling, and complex retrieval performance, achieving relative improvements of more than 12\% in certain categories. These results highlight the effectiveness of jointly modeling memory evolution and adaptive evidence acquisition for long-term agent interactions.
