让对话记忆具备结构化关系，提升长对话推理能力。
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
- 生成时注入关系图、时间事件链和话题摘要三类结构化信息
- 在多个基准上平均提升评分7.5%至10.1%，最弱模型提升达12.2%
- 无需修改主模型架构，适配性强，适合各类对话系统
长时对话智能体依赖日益复杂的记忆检索机制，但通常将检索片段作为无结构文本输入语言模型，缺乏关系、时间与主题结构，影响复杂推理。为此，我们提出GRAVITY（Generation-time Relational Anchoring via Injected Topological Memory），一个即插即用的结构化记忆模块。GRAVITY从原始对话中提取三类互补知识表示：基于关系图的实体画像、连接成因果链的时间事件元组，以及跨会话的话题摘要。生成时，将这些表示以结构化锚定上下文注入主系统提示。该方法在不修改主模型架构的前提下，有效整合分散证据，形成连贯且相关查询的上下文。在LongMemEval与LoCoMo五个不同记忆系统上的评估显示，平均提升LLM-judge准确率7.5%–10.1%；基线越弱，增益越大——最弱系统提升12.2%，最强系统仍获3.8%–5.7%提升。结果表明，结构化上下文锚定是一种普适有效的架构无关增强范式。
原文摘要 · Abstract (English)
Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typically fed to the language model as unstructured text, lacking the relational, temporal, and thematic structures essential for complex reasoning. To bridge this reasoning gap, we introduce GRAVITY (\textbf{G}eneration-time \textbf{R}elational \textbf{A}nchoring \textbf{V}ia \textbf{I}njected \textbf{T}opological Memor\textbf{Y}), a plug-and-play structured memory module. GRAVITY extracts three complementary knowledge representations from raw conversational utterances: entity profiles grounded in relational graphs, temporal event tuples linked into causal traces, and cross-session topic summaries. At generation time, it injects these representations into the host system's prompt as structured anchoring contexts. This approach effectively synthesizes scattered evidence into a coherent, query-relevant context without requiring any architectural modifications to the host model. Extensive evaluations across five diverse memory systems on the LongMemEval and LoCoMo benchmarks demonstrate the efficacy of our approach. On average, GRAVITY improves LLM-judge accuracy by 7.5--10.1%. Gains are inversely correlated with baseline strength: the weakest host improves by 12.2% while the strongest still gains 3.8--5.7%. These findings establish structured context anchoring as a broadly effective, architecture-agnostic augmentation paradigm for long-horizon conversational memory.
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。