让大模型长程记忆既高效又可解释，用隐式图存信息，显式检索关键子图。
Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
- 隐式图存记忆，提升稳定性和效率；显式子图检索，便于检查和推理。
- 在多个长程任务上优于现有显式图与隐式记忆方法，效果随模型规模提升。
- 适合需要可解释性且处理长上下文的场景，如复杂问答与文档推理。
长程应用越来越要求大语言模型在证据稀疏、分散于超长上下文时仍能准确回答问题。现有记忆系统主要分为两类：显式结构化记忆可解释性强但易受长上下文干扰，而隐式记忆机制高效稳定却难以审查。我们提出 LatentGraphMem，一种结合隐式图记忆与显式子图检索的记忆框架。该框架在隐空间中存储图结构记忆以保证稳定与高效，并提供任务相关的子图检索接口，在固定预算下返回紧凑的符号子图，供下游推理和人工检查。训练时，通过显式图视图对接冻结推理器进行问答监督；推理时，子图在隐空间中检索，仅结果被外部化。在多模型规模下的长程基准测试中，LatentGraphMem 持续超越代表性显式图与隐式记忆基线，同时支持参数高效的适应与灵活扩展至更大推理器，不引入大量符号冗余。
原文摘要 · Abstract (English)
Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit structured memories offer interpretability but often become brittle under long-context overload, while latent memory mechanisms are efficient and stable yet difficult to inspect. We propose LatentGraphMem, a memory framework that combines implicit graph memory with explicit subgraph retrieval. LatentGraphMem stores a graph-structured memory in latent space for stability and efficiency, and exposes a task-specific subgraph retrieval interface that returns a compact symbolic subgraph under a fixed budget for downstream reasoning and human inspection. During training, an explicit graph view is materialized to interface with a frozen reasoner for question-answering supervision. At inference time, retrieval is performed in latent space and only the retrieved subgraph is externalized. Experiments on long-horizon benchmarks across multiple model scales show that LatentGraphMem consistently outperforms representative explicit-graph and latent-memory baselines, while enabling parameter-efficient adaptation and flexible scaling to larger reasoners without introducing large symbolic artifacts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。