Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts severely limit their effectiveness in long-term dialogue agents. External memory systems have been proposed to improve memory maintenance. However, these systems mainly rely on one-shot retrieval, which limits their ability to retrieve sufficient and relevant evidence. Although recent methods introduce reflection into retrieval, their retrieval paths are generated by the LLM from limited evidence, leading to unstable retrieval and additional latency overhead. %These limitations highlight the need for effective retrieval mechanisms. To address these limitations, we propose MGRetrieval, a retrieval strategy that grounds reflective retrieval in the semantic structure of historical memories. Specifically, MGRetrieval consists of two steps: (1) It references the structure of historical memories to construct a more precise retrieval path. (2) The LLM retains critical memories and determines whether accumulated memories are sufficient to stop further iterative retrieval. This allows the retrieval process to follow semantically meaningful paths. Through memory-guided retrieval and critical memory propagation, MGRetrieval gradually constructs concise and sufficient memory contexts. Extensive experiments on LoCoMo show that MGRetrieval outperforms the strongest baseline by 8.91\% in F1 and 11.11\% in BLEU-1 on average across Qwen2.5-14B and Qwen3-14B, while maintaining practical token and latency costs. The code can be found in https://anonymous.4open.science/r/MGRetrieval.

翻译：大型语言模型（LLMs）在对话领域取得显著进展，但冗余的记忆上下文严重限制了其在长期对话智能体中的有效性。已有研究提出外部记忆系统以改进记忆维护，但这些系统主要依赖单次检索，导致难以获取充分且相关的证据。尽管近期方法将反思引入检索过程，但其检索路径由LLM基于有限证据生成，导致检索不稳定并带来额外延迟开销。针对这些局限，我们提出MGRetrieval——一种将反思式检索锚定于历史记忆语义结构的检索策略。具体而言，MGRetrieval包含两个步骤：（1）参照历史记忆结构构建更精确的检索路径；（2）LLM保留关键记忆并判断累积记忆是否足以终止迭代检索，使得检索过程遵循语义有效的路径。通过记忆引导检索与关键记忆传播，MGRetrieval逐步构建简洁且充分的记忆上下文。在LoCoMo上的大量实验表明，在Qwen2.5-14B与Qwen3-14B上，MGRetrieval相较最强基线平均F1值提升8.91%，BLEU-1值提升11.11%，同时保持实用的词元与延迟成本。代码已发布于https://anonymous.4open.science/r/MGRetrieval。