提出可隐式跨实体推理的叙事记忆架构，解决长时记忆多跳关联难题。
Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative Profiles
- 用叙事中自然出现的实体名做字符串匹配，实现无需构建图谱的跨实体遍历。
- 在MemHop和LoCoMo上分别达到80.1%和78.4%准确率，超越多个基线模型。
- 证明记忆结构中的扩展与压缩机制各有专长，适合不同任务场景。
长期记忆对跨会话交互的LLM代理至关重要，但现有基准主要评估单跳回忆，未涵盖多跳关联。本文提出三个贡献：首先，构建了包含1000个问题、覆盖1-5跳深度的多跳记忆基准MemHop，涵盖10种社交网络场景，并提供每跳证据标注；其次，提出两层记忆架构Profile-Graph Memory（ProGraph），包括（i）叙事扩展：通过字符串匹配自动遍历叙述中自然出现的实体名，替代显式知识图谱构建；（ii）压缩残差：在每次更新时无额外API开销地提取精确日期、数量及命名项；第三，全网格消融实验表明：叙事扩展主导多跳推理（移除后MemHop下降22.6个百分点），压缩残差提升精准召回（不共提取时LoCoMo下降8.6个百分点），且跨机制影响小于3个百分点。ProGraph在MemHop上平均达80.1%（媲美FullContext），在LoCoMo上达78.4%（领先FullContext 11.3个百分点），优于Mem0、A-Mem、HippoRAG和RAG。相关代码与数据已开源。
原文摘要 · Abstract (English)
Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving multi-hop association largely unmeasured. We make three contributions. First, we introduce MemHop, a multi-hop memory benchmark of 1,000 questions at hop depths 1-5 across 10 social-network scenarios, with per-hop evidence annotations. Second, we present Profile-Graph Memory (ProGraph), a two-layer memory architecture combining (i) profile expansion -- substring-matched traversal of entity names that naturally appear in LLM-written profile narratives, a minimal alternative to explicit knowledge-graph construction -- and (ii) compression residuals -- exact dates, quantities, and named items co-extracted with each profile update at zero extra API cost. Third, a full-grid ablation shows cross-benchmark mechanism specialization: profile expansion drives multi-hop reasoning (-22.6pp on MemHop when removed) while compression residuals drive precision recall (-8.6pp on LoCoMo when not co-extracted), with cross-effects under 3pp within a single architecture. ProGraph averages 80.1% on MemHop (matching the FullContext reference) and 78.4% on LoCoMo (exceeding FullContext by 11.3pp), outperforming Mem0, A-Mem, HippoRAG, and RAG on both. We release MemHop, ProGraph, and baseline implementations.
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。