学习用户感知的回忆：长期对话记忆中的个性化检索
Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
AI总结：
提出PPRO框架，通过用户画像引导的排序和基于GRPO的查询重写，实现个性化记忆检索，在LoCoMo和LongMemEval-S上取得一致提升。
摘要：
长期对话智能体应能记住过去的交互，但记忆只有在为正确的用户回忆起正确的证据时才有用。现有的记忆增强型LLM智能体在构建紧凑记忆库方面取得了进展，但检索仍常由以查询为中心的相似性或固定排序规则驱动，忽略了用户条件相关性。为解决这一问题，我们提出画像引导的个性化检索优化（PPRO），这是一个以检索为中心的框架，使记忆检索既具有用户感知又具有个性化。它从对话历史中构建情景和语义记忆库，并从累积的对话中推导出用户画像。该画像作为记忆排序中的显式个性化先验，使检索能够考虑稳定的用户属性、偏好和需求。我们进一步使用组相对策略优化训练查询重写器，以证据检索质量和下游答案质量作为反馈，同时保持记忆库和答案模型冻结。在LoCoMo和LongMemEval-S上的实验表明，与无训练记忆系统和基于训练的系统相比，PPRO取得了一致的提升。消融研究进一步表明，画像引导的排序和面向检索的重写都对性能有显著贡献，突显了检索优化在个性化长期记忆使用中的关键作用。
英文摘要：
Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in building compact memory banks, yet retrieval is still often driven by query-centered similarity or fixed ranking rules, leaving user-conditioned relevance underexplored. To address this gap, we propose Profile-guided Personalized Retrieval Optimization (PPRO), a retrieval-centric framework that makes memory retrieval both user-aware and optimizable. PPRO builds episodic and semantic memory banks from dialogue histories and derives a user profile from accumulated memories. The profile serves as an explicit personalized prior in memory ranking, allowing retrieval to account for stable user attributes, preferences, and relationships. PPRO further trains a query rewriter with Group Relative Policy Optimization, using both evidence retrieval quality and downstream answer quality as feedback while keeping the memory banks and answer model fixed. Experiments on LoCoMo and LongMemEval-S show consistent gains over training-free memory systems and training-based baselines. Ablation studies further show that both profile-guided ranking and retrieval-oriented rewriting contribute substantially to performance, highlighting retrieval optimization as a key factor in personalized long-term memory use.
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。
