APDMem：面向查询自适应长期记忆的智能体控制渐进式披露
APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory
- Machine Learning Center of Excellence, JPMorgan Chase & Co.（摩根大通卓越机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
APDMem提出一种智能体控制的渐进式披露记忆架构，通过分层检索和自适应成本-保真度权衡，在长对话记忆中高效恢复证据，仅访问8%对话即达强性能。
AI中文摘要：
个性化LLM助手必须从跨不同复杂度查询的长对话历史中恢复稀疏证据。我们引入了APDMem（智能体控制的渐进式披露记忆），一种分层长期记忆架构，将渐进式披露应用于记忆检索。APDMem不依赖扁平记忆存储或固定检索粒度，而是将对话历史表示为四个逐步详细的层：主题摘要、个性化关键事实、回合级证据笔记和原始消息。在推理时，控制器对记忆层次应用渐进式披露：它首先读取高级摘要，仅在需要时深入细粒度证据。这创建了自适应成本-保真度权衡：简单查询可以提前终止，而复杂的时序、多跳或精确证据查询触发更深入的检查。笔记合成器将检索到的证据转换为查询聚焦的结构，在最终答案生成之前整合事实、排序事件并标记矛盾。在LongMemEval上的实验表明，APDMem在长上下文记忆推理中实现了强性能，同时仅访问总对话的8%。
英文摘要：
Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (Agent-controlled Progressive Disclosure Memory), a hierarchical long-term memory architecture that applies progressive disclosure to memory retrieval. Rather than relying on a flat memory store or fixed retrieval granularity, APDMem represents conversation history as four progressively detailed layers: thematic summaries, personalized key facts, turn-level evidence notes, and raw messages. At inference time, a controller applies progressive disclosure to the memory hierarchy: it first reads high-level summaries and drills into finer evidence only when needed. This creates an adaptive cost-fidelity trade-off: simple queries can terminate early, while complex temporal, multi-hop, or exact-evidence queries trigger deeper inspection. A note synthesizer converts retrieved evidence into a query-focused structure that consolidates facts, orders events, and flags contradictions before final answer generation. Experiments on LongMemEval show that APDMem achieves strong performance for long-context memory reasoning while accessing only 8% of the total conversations.
