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

• URL: http://arxiv.org/abs/2609.17010v1
• Date: Tue, 15 Sep 2026 11:21:39 GMT
• Title: ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
• Abstract summary: ThinkFlow is a novel end-to-end latent memory framework for lifelong conversational agents.<n>It bypasses the text bottleneck by compressing conversational flows into probabilistic latent memory skills.<n>It provides highly personalized and contextually accurate responses over extended multi-session interactions.
• Score: 30.033481918192987
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding [64.34948094316685]
  We introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize.<n>LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T17:28:14Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• LifeSide: Benchmarking Agents as Lifelong Digital Companions [47.43438363687746]
  benchmark is a benchmark centered on multi-session textitMemory-Emotion-Environment loops.<n>By modeling users as persistent worlds with layered profiles and event trajectories, benchmark uses multi-agent simulation to project environmental dynamics into dialogue.<n>Our experiment results reveal a stark reality: even models that saturate current memory benchmarks fail to sustain accurate user understanding and true companionship over long horizons.
  arXiv  Detail & Related papers  (2026-06-03T09:37:25Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• Evaluating Memory Capability in Continuous Lifelog Scenario [18.42798691109198]
  Existing benchmarks primarily focus on online one-on-one chatting or human-AI interactions.<n>We propose a hierarchical synthesis framework to curate textbftextscLifeDialBench<n>We also propose an textbfOnline Evaluation protocol that strictly adheres to temporal causality.
  arXiv  Detail & Related papers  (2026-04-13T08:42:43Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• MemVerse: Multimodal Memory for Lifelong Learning Agents [35.218549149012844]
  We introduce MemVerse, a model-agnostic, plug-and-play memory framework.<n>MemVerse bridges fast parametric recall with hierarchical retrieval-based memory.<n>It enables scalable and adaptive multimodal intelligence.
  arXiv  Detail & Related papers  (2025-12-03T10:06:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.