构建分层记忆树，让大模型更懂人的长期互动关系
PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
- 用三层树状结构记录人物认知，证据与结论路径清晰可追溯
- 在18项测试中12项排名第一，6项进入前二，表现全面领先
- 适合需要长期理解用户画像的智能助手、对话代理等场景
持久性大模型代理需要能够显式表达长期交互中人物理解形成过程的记忆机制。现有方法侧重信息存储与检索，却未能说明积累的交互证据如何抽象为人物认知。本文将此过程视为模式建构，将具体情境证据抽象为可复用的模式和稳定的人物层面判断。提出PersonaTree——一种分层生命周期记忆框架，通过三层次人物树实现该理念，并建立从证据到结论的显式支持路径。该框架采用保守写入、置信度驱动合并及查询感知路径检索策略，仅返回满足当前查询所需的证据深度。在六个涉及人物理解与持久记忆的基准上，使用三种回答模型进行测试，PersonaTree在18个子任务中的12项取得最优成绩，16项进入前二。消融实验表明，层级结构提升了KnowMe数据集上的抽象理解能力，而支持路径检索在相近上下文预算下增强了RealPref对齐效果。
原文摘要 · Abstract (English)
Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet give limited account of how accumulated interaction evidence is abstracted into person understanding. We view this process as schema formation, where situated evidence is abstracted into reusable patterns and stable person level claims. We introduce PersonaTree, a structured lifecycle memory framework that realizes this view as a three level persona tree with explicit support paths from evidence to claims. PersonaTree maintains the tree through conservative writing, confidence guided consolidation, and query conditioned path retrieval, returning only the evidence depth required by each query. Across six person understanding and persistent memory benchmarks with three answer backbones, PersonaTree ranks first in 12 of 18 compact scores and reaches the top two in 16 settings. Ablations show that hierarchy improves abstract person understanding on KnowMe, while support path retrieval improves RealPref alignment under a comparable context budget.
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。