前瞻性引导的记忆检索：语言模型中的记忆检索
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
AI总结：
前瞻性引导的记忆检索通过模拟未来步骤来增强长周期检索，提升用户个性化需求的响应质量。
摘要：
长周期个性化要求对话助手从扩展的交互历史中检索用户特定的事实。在实践中，许多相关事实与查询在语义相似度上较低。标准的检索增强生成（RAG）和图RAG系统仍然主要是回顾性的：它们依赖于查询与嵌入的相似度或固定的图遍历，因此常常错过对用户需求重要的事实，但这些事实远离查询在嵌入空间中。受前瞻性能力的启发，即人类利用想象的未来作为回忆的线索，我们引入了前瞻性引导检索（PGR），将检索与记忆存储的方式解耦。给定一个用户查询，PGR首先将目标扩展为一个简短的思维树（ToT）或线性链的合理下一步步骤，并使用这些步骤作为检索探针，而不是仅依赖原始查询。通过这些探针检索到的事实随后用于个性化下一步的前瞻性，使PGR能够发现只有在模拟扎根于用户历史后才相关的额外记忆。我们还引入了MemoryQuest，一个具有挑战性的多会话基准，在其中每个查询都被注释为3-5个带有日期的参考事实，这些事实受低查询-参考相似度约束。在1,625个查询中，覆盖185个用户档案的3个公开可用数据集中，PGR-TOT在检索方面显著改进，包括在MemoryQuest上相对于最强基线的近3倍召回率。在LLM作为判断者的成对比较中，PGR生成的响应在89-98%的查询中优于基线，盲注人类注释在保留的子集上显示相同趋势。总体而言，结果表明，显式的前瞻性在长周期检索和响应质量方面相对于仅基于相似度的基线具有显著优势。
英文摘要：
Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low semanticsimilarity to the query under dense retrieval. Standard Retrieval-Augmented Generation (RAG) and GraphRAG systems are still largely retrospective: they rely on embedding similarity to the query or on fixed graph traversals, so they often miss facts that matter for the user's needs but lie far from the query in embedding space. Inspired by prospection, the human ability to use imagined futures as cues for recall, we introduce Prospection-Guided Retrieval (PGR), which decouples retrieval from how memories are stored. Given a user query, PGR first expands the goal into a short Tree-of-Thought (ToT) or linear chain of plausible next steps, and uses these steps as retrieval probes rather than relying on the original query alone. The facts retrieved by these probes are then used to personalize the next round of prospection, enabling PGR to uncover additional memories that become relevant only after the simulation is grounded in the user's history. We also introduce MemoryQuest, a challenging multi-session benchmark in which each query is annotated with 3--5 dated reference facts subject to a low query-reference similarity constraint. Across 1,625 queries spanning 185 user profiles from 3 publicly available datasets, PGR-TOT substantially improves retrieval, including nearly 3x recall on MemoryQuest over the strongest baseline. In pairwise LLM-as-judge comparisons against baselines, PGR-generated responses are preferred on 89--98% of queries, with blinded human annotations on held-out subsets showing the same trend. Overall, the results demonstrate that explicit prospection yields large gains in long-horizon retrieval and response quality relative to similarity-only baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
