APEX-MEM: 基于时序推理的代理半结构化记忆用于长期对话AI
APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
AI总结：
APEX-MEM通过结合属性图、只追加存储和多工具检索代理，解决大语言模型在长期对话记忆中的可靠性问题，实现88.88%的LOCOMO问答准确率和86.2%的LongMemEval表现。
摘要：
大型语言模型在可靠长期对话记忆方面仍面临挑战：单纯扩大上下文窗口或应用简单检索常引入噪声并破坏响应稳定性。我们提出了APEX-MEM，一种对话记忆系统，结合三个关键创新：(1) 使用领域无关本体将对话结构化为以实体为中心的时序事件属性图；(2) 只追加存储保留信息的完整时序演变；(3) 多工具检索代理在查询时理解并解决冲突或变化的信息，生成紧凑且上下文相关的记忆摘要。这种检索时的解决方法保留完整交互历史并抑制无关细节。APEX-MEM在LOCOMO问答任务上达到88.88%的准确率，在LongMemEval上达到86.2%，优于最先进的会话感知方法，证明了结构化属性图能够实现更时序一致的长期对话推理。
英文摘要：
Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory system that combines three key innovations: (1) a property graph which uses domain-agnostic ontology to structure conversations as temporally grounded events in an entity-centric framework, (2) append-only storage that preserves the full temporal evolution of information, and (3) a multi-tool retrieval agent that understands and resolves conflicting or evolving information at query time, producing a compact and contextually relevant memory summary. This retrieval-time resolution preserves the full interaction history while suppressing irrelevant details. APEX-MEM achieves 88.88% accuracy on LOCOMO's Question Answering task and 86.2% on LongMemEval, outperforming state-of-the-art session-aware approaches and demonstrating that structured property graphs enable more temporally coherent long-term conversational reasoning.
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。
