Trained Persistent Memory for Frozen Decoder-Only LLMs

arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However,

arXiv:2604.09852v1 Announce Type: new Abstract: Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state.

arXiv:2603.18743v1 Announce Type: new Abstract: We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing

arXiv:2609.29144v1 Announce Type: new Abstract: Persistent memory lets language-model agents improve prompts and skills without updating model weights. We show that matching

arXiv:2605.00356v1 Announce Type: cross Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive

arXiv:2604.05887v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is

arXiv:2604.27707v1 Announce Type: new Abstract: Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not

arXiv:2605.00422v1 Announce Type: cross Abstract: Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder