让大模型记忆更懂上下文，避免混淆相似信息
Grounding Agent Memory in Contextual Intent
- 用意图三要素索引记忆，精准区分相似内容
- 在长对话中提升检索准确率35.6%，越长越有效
- 适合需要长期推理的智能助手、复杂任务系统
在长时序、目标导向的交互中部署大语言模型仍具挑战性，因相似实体和事实在不同隐含目标与约束下重复出现，导致记忆系统检索到不匹配上下文的信息。本文提出STITCH（结构化意图上下文历史追踪）——一种代理式记忆系统，为每个轨迹步骤添加结构化检索线索：上下文意图，并根据当前步骤意图进行历史检索。上下文意图包含三个关键信号：当前隐含目标（定义主题段）、动作类型、以及关键实体类型（决定哪些属性重要）。推理时，STITCH通过意图兼容性过滤并优先排序记忆片段，抑制语义相似但上下文不匹配的历史。为评估，我们引入CAME-Bench，一个面向真实动态、目标导向轨迹的上下文感知检索基准。在CAME-Bench与LongMemEval上，STITCH达到当前最优性能，优于最强基线35.6%，且随轨迹长度增加，优势更显著。分析表明，意图索引显著降低检索噪声，支持意图感知的记忆机制以实现稳健的长时序推理。
原文摘要 · Abstract (English)
Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and constraints, causing memory systems to retrieve context-mismatched evidence. We propose STITCH (Structured Intent Tracking in Contextual History), an agentic memory system that indexes each trajectory step with a structured retrieval cue, contextual intent, and retrieves history by matching the current step's intent. Contextual intent provides compact signals that disambiguate repeated mentions and reduce interference: (1) the current latent goal defining a thematic segment, (2) the action type, and (3) the salient entity types anchoring which attributes matter. During inference, STITCH filters and prioritizes memory snippets by intent compatibility, suppressing semantically similar but context-incompatible history. For evaluation, we introduce CAME-Bench, a benchmark for context-aware retrieval in realistic, dynamic, goal-oriented trajectories. Across CAME-Bench and LongMemEval, STITCH achieves state-of-the-art performance, outperforming the strongest baseline by 35.6%, with the largest gains as trajectory length increases. Our analysis shows that intent indexing substantially reduces retrieval noise, supporting intent-aware memory for robust long-horizon reasoning.
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。