发表机构
Pengcheng Laboratory; Harbin Institute of Technology, Shenzhen; China Unicom Greater Bay Area Innovation Institute（鹏城实验室; 哈尔滨工业大学（深圳）; 中国联通粤港澳大湾区创新研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对终身对话代理记忆瓶颈，提出ThinkFlow潜在记忆框架，通过概率潜在技能压缩与测试时进化实现无标签个性化，实验优于现有系统。
AI 中文摘要
终身对话代理依赖记忆系统来维持与用户的深度、上下文感知交互。然而，现有的显式文本记忆流水线存在严重的信息瓶颈，常常丢失微妙的行为模式和情感变化。此外，这些系统在部署后通常是静态的，无法在没有手动反馈的情况下自主适应个人习惯和偏好。然而，认知科学表明，人类在纯潜在空间中维持心理模型，并通过预测编码不断对其进行细化。受此启发，我们提出了ThinkFlow，一种用于终身对话代理的新型端到端潜在记忆框架。ThinkFlow通过将对话流动态压缩为概率潜在记忆技能来绕过文本瓶颈，自主地将复杂的用户状态整合为无语义干扰的解纠缠连续向量。为了打破这一障碍，我们引入了一种测试时进化范式。通过将教师引导的潜在对齐用于初始化状态，并结合自监督的下一个用户话语预测任务进行持续细化，该框架成功克服了冷启动挑战，实现了无标签的终身个性化。在长期对话基准上的大量实验表明，ThinkFlow显著优于现有的记忆系统，在扩展的多会话交互中提供高度个性化和上下文准确的响应。
英文摘要
Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a severe information bottleneck, often losing subtle behavioral patterns and emotional shifts. Furthermore, being typically static post-deployment, they cannot autonomously adapt to personal habits and preferences without manual feedback. Cognitive science, however, suggests that humans maintain mental models purely in a latent space and continuously refine them through predictive coding. Inspired by this, we propose \textbf{ThinkFlow}, a novel end-to-end latent memory framework for lifelong conversational agents. ThinkFlow bypasses the text bottleneck by dynamically compressing conversational flows into probabilistic latent memory skills, autonomously consolidating complex user states into disentangled, continuous vectors without semantic interference. To break this barrier, we introduce a test-time evolution paradigm. By coupling teacher-guided latent alignment to bootstrap the initial state with a self-supervised next-user-utterance prediction task for continuous refinement, the framework successfully overcomes cold-start challenges and achieves label-free lifelong personalization. Extensive experiments on long-term conversation benchmarks demonstrate that ThinkFlow significantly outperforms prevailing memory systems, providing highly personalized and contextually accurate responses over extended multi-session interactions.
