CABLE：通过基于互补前项的链接与扩展扩展记忆检索的覆盖范围
CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion
浏览论文内容
中文总结 AI 辅助
CABLE是一种插件式记忆检索增强模块，通过构建互补关联扩展检索覆盖范围，在多个模型和数据集上的系统级评估中提升了证据可及性的LLM评判分数。
中文摘要 AI 辅助
当大语言模型（LLM）智能体在结构化工作流和会话中运行时，保留长期历史并不能确保后续上下文能通过有限的记忆接口恢复相关证据。我们研究长期对话记忆中的证据可及性问题，该问题中检索仍严重依赖语义相似性。这种方法在主题回忆方面表现良好，但常常遗漏与后续事件语义距离较远的早期经验、计划或动机，而这些正是解释后续事件的关键。现有的记忆图提供了跨记忆结构，但主要由语义重叠驱动的链接会重复主检索器已能恢复的内容。我们认为链接构建应优先考虑一组稀疏的、与检索器互补的关联。我们提出了CABLE（Complementary Antecedent-Based Linking and Expansion，基于互补前项的链接与扩展），这是一种插件式增强模块，用于构建旨在扩展主检索器直接语义覆盖范围的链接。对于每个新记忆，CABLE会生成面向前项的查询，检索先前的记忆，减去直接语义邻域中的候选，并在将接受的互补关联添加到稀疏有向图后进行验证。在检索时，CABLE会沿这些链接扩展主系统的检索种子，以呈现隐式支持证据。我们在LoCoMo和MA-LongMemEval数据集上使用A-MEM评估CABLE，并进一步将其集成到LoCoMo上的SimpleMem和Mem0g中，使用的模型包括Qwen3.5-27B、DeepSeek-chat和GPT-4o-mini。CABLE在所有评估的系统级设置中均产生更高的平均LLM评判分数，在有用证据分布在多个记忆或会话的类别中（包括开放域、多会话和偏好导向问题）获得最大增益。这些结果支持优先考虑稀疏的、与主检索器互补而非重复的、与推理相关的关联。
英文摘要
As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded memory interface. We study this evidence-reachability problem in long-term conversational memory, where retrieval still relies heavily on semantic similarity. This works well for topical recall, but it often misses earlier experiences, plans, or motivations that are semantically distant from the later events they help explain. Existing memory graphs provide cross-memory structure, yet links driven mainly by semantic overlap can duplicate what the host retriever already recovers. We argue that link construction should instead prioritize a sparse set of retriever-complementary associations. We present CABLE (Complementary Antecedent-Based Linking and Expansion), a plug-in augmentation that constructs links designed to extend the host retriever's direct semantic reach. For each new memory, CABLE generates antecedent-oriented queries, retrieves prior memories, subtracts candidates in the direct semantic neighborhood, and verifies the remainder before adding the accepted complementary associations into a sparse directed graph. At retrieval time, CABLE expands the host system's retrieved seeds along these links to surface implicit supporting evidence. We evaluate CABLE with A-MEM on LoCoMo and MA-LongMemEval, and further integrate it into SimpleMem and Mem0g on LoCoMo, using Qwen3.5-27B, DeepSeek-chat, and GPT-4o-mini. CABLE yields higher mean LLM-judge scores in every evaluated system-level setting, with the largest gains in categories where useful evidence is distributed across memories or sessions, including open-domain, multi-session, and preference-oriented questions. These results support prioritizing sparse, reasoning-relevant associations that complement rather than duplicate the host retriever.
发表机构
- Shanghai Jiao Tong University（上海交通大学）
- Shanghai Innovation Institute（上海创新研究院）
机构由 AI 辅助整理，请以论文原文为准。
