发表机构
China Mobile Information Technology Co., Ltd.（中国移动信息技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出HERO框架，通过异构记忆图保留原始对话文本，结合人像优化检索，在两个基准数据集上提升了智能体的事实与个性化推理性能。
AI 中文摘要
长期记忆对于个性化响应和长时程智能体交互至关重要。现有方法通常依赖大语言模型（LLM）压缩或重写对话历史，并将转换后的记忆作为检索证据。尽管在组织碎片化上下文方面取得了进展，但仍存在两个主要缺陷：（1）压缩导致的信息损失，会丢弃后续可能有用的细粒度细节；（2）重写导致的语义漂移，会侵蚀原始语气和情境上下文。本研究提出一种面向智能体长期记忆的新型人像增强检索优化框架HERO。具体而言，HERO将对话历史转换为可追踪的异构记忆图，保留原始对话文本作为推理证据，从而缓解信息损失；在检索阶段，HERO从当前查询中提取初始锚点，并通过迭代图遍历纳入人像信息，这些锚点和人像提供的引导信号可自适应激活图中信息最丰富的区域。在两个基准数据集上的实验表明，HERO在事实推理和个性化推理方面均优于强基线，同时能更忠实地访问原始对话证据。
英文摘要
Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite dialogue histories and use the transformed memories as retrieval evidence. Despite the progress in organizing fragmented contexts, two major drawbacks persist: (1) information loss from compression, which discards fine-grained but later useful details, and (2) semantic drift from rewriting, which erodes the original tone and situated context. In this work, we propose a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO). Specifically, HERO converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss. For retrieval, HERO extracts initial anchors from the current query and incorporates human profiles via an iterative graph traversal; these anchors and profiles provide guidance signals that adaptively activate the most informative regions of the graph. Experiments on two benchmark datasets show that HERO outperforms strong baselines on both factual and personalized reasoning, while providing more faithful access to raw dialogue evidence.
