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
Sep 16
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
Sep 30
ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents
ReMem is a new recommendation agent framework that rethinks perception and memory for long-context recommendation tasks. It replaces raw HTML parsing with OCR-based multimodal perception from screenshots, extracting structured information in a platform-agnostic way. The framework also introduces a chunk-wise sequential memory update strategy and a multi-memory GRPO variant to efficiently model evolving user preferences over arbitrarily long interaction histories, achieving a 5.16% average improvement over state-of-the-art baselines on three recommendation agent 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 Computation and Language
2d ago
Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants
Scalaris is a scalable enterprise memory architecture designed to balance retrieval accuracy and context efficiency for conversational AI assistants. It separates user interactions and assistant responses into distinct long‑term and short‑term memory streams, each with specialized representations and ingestion/retrieval pipelines. The system achieves state‑of‑the‑art benchmark scores while reducing retrieved context tokens by about tenfold and improving overall response quality by 36 % in proprietary deployments.