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.
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.
InteraCtive Memory Learning is proposed, a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy that significantly outperforms strong baselines.
Cai Ke, Jiang-Yue Yan, Han Zhang et al.· 1 citation
A novel recommendation agent framework, termed as ReMem, that combines OCR-based multimodal perception with time-evolving dynamic memory, which allows the agent to preserve evolving user preferences without relying on external memory modules or disrupting the standard autoregressive generation process.
A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per memory...
LGM is presented, a novel neuro-symbolic framework that shifts long-term memory disentanglement into a continuous latent space and significantly outperforms state-of-the-art baselines in capturing both explicit and implicit preferences while enabling personalized responses.
Cai Ke, Xing-Hao Chen, Xiao-Yu Shen et al.· 1 citation
SimLife is introduced, a scalable platform for simulating long-term household life with rich visual observations, ground-truth action logs, and synthetic dialogues with audio that evaluates long-context pattern understanding: the ability to infer latent behavioral rules from weeks or months of everyday observations.
Run Peng, Zinnia Nie, Jing Ding et al.· arXiv.org· 0 citations
This work introduces MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader and proposes MemOpt, a reinforcement learning framework that optimizes the memory writer to produce faithful, informative, and retrievable memories.
Guang-Zhi Xiong, Xin-Yuan Zhang, Xiao Yang et al.· arXiv.org· 0 citations