ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents

2026-09-15

AI Summary

为解决长期对话代理中信息瓶颈和适应性问题，提出ThinkFlow框架，通过动态压缩对话流至概率潜在记忆，并采用测试时进化范式实现持续个性化。

Abstract

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.

Problem

• lifelong conversational agents
• information bottleneck
• latent memory
• context-aware interactions
• personal habits and preferences

Innovation

• probabilistic latent memory
• end-to-end framework
• test-time evolution
• lifelong personalization
• context-aware interactions