隐式图，显式检索：迈向高效且可解释的长周期记忆 для 大语言模型
Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
AI总结：
LatentGraphMem结合隐式图记忆与显式子图检索，实现高效且可解释的长周期记忆，提升大语言模型的推理能力与可解释性。
摘要：
长周期应用日益要求大型语言模型（LLMs）在相关证据稀少且分散于非常长的上下文中的情况下回答查询。现有的记忆系统主要遵循两种范式：显式结构化记忆提供可解释性，但在长上下文过载时往往变得脆弱；而潜在记忆机制则高效且稳定，但难以检查。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。LatentGraphMem在潜在空间中存储图结构的记忆以保证稳定性和效率，并暴露一个任务特定的子图检索接口，该接口在固定预算下返回一个紧凑的符号子图，用于下游推理和人类检查。在训练过程中，显式图视图被生成以与冻结的推理器接口，以进行问题回答监督。在推理过程中，检索在潜在空间中进行，仅检索到的子图被外部化。在多个模型规模的长周期基准测试中，实验表明LatentGraphMem在显式图和潜在记忆基线中表现一致优异，同时实现了参数高效适应和灵活扩展到更大推理器，而无需引入大规模符号 artifacts。
英文摘要：
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.
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。
