arXiv AI
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
4d ago
Interactive Memory Learning for Long-Term Conversations
arXiv:2609.17088v1 Announce Type: new Abstract: Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these...
arXiv Computation and Language
Aug 27
Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory
The paper introduces HiPS, a hierarchical strategy co‑evolution framework for memory‑augmented agents that separates memory management into a globally shared foundation and a user‑specific adaptive tier. HiPS uses a Universal Strategy to capture shared principles from cross‑persona trajectories, Persona Delta Distillation to create tailored rules for users deviating from general patterns, and Cross‑Level Rule Flow to dynamically adjust the boundary between global and personal rules. Experiments show that this approach consistently outperforms existing memory‑augmented baselines.
arXiv AI
Jul 7
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
arXiv:2607. 03093v1 Announce Type: cross Abstract: Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks.
arXiv AI
Jun 3
RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
arXiv:2510. 16392v3 Announce Type: replace Abstract: Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states.
arXiv AI
Sep 11
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
PRAGMA is a benchmark designed to evaluate personalized guidance in long‑term conversations. It includes curated longitudinal conversation histories, evidence annotations, and guidance scenarios that reflect evolving user contexts and incorrect assumptions. Experiments show that current retrieval, memory, and long‑context models struggle to recover relevant conversational evidence and to use it effectively for personalized guidance.
arXiv Machine Learning
Aug 4
Learning What to Remember: Test-Time Training via Context Distillation
arXiv:2608. 01672v1 Announce Type: cross Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later.