发表机构
Southern University of Science and Technology; Xidian University（南方科技大学; 西安电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对长期运行LLM推理中上下文切换导致状态不连续的问题，提出LiveMem方法，通过引入独立于活跃上下文的持久记忆状态，实现状态连续性，在LongMemEval等测试中表现领先。
AI 中文摘要
长期运行的助手和智能体会消耗交互流，最终交互流会超出上下文的承载能力。现有的上下文保留、摘要生成和检索方法虽能保留对部分历史的访问权限，但在工作上下文发生变化时，无法在整个生命周期内提供持久状态。我们将这一缺失的推理能力定义为“上下文切换下的状态连续性”：通过固定容量的记忆状态传递计算，该记忆状态的生命周期与活跃上下文无关。我们提出一种内在记忆方法LiveMem，它在预训练的全注意力大语言模型中增加了一个记忆状态，该状态可在整个生命周期内保留历史信息，同时主注意力路径保留有界的键值窗口。上下文切换与记忆状态维护、面向记忆的后训练、状态感知服务三者协同，使得该记忆状态在其原始 token 被释放后仍能发挥重要作用。实验表明，LiveMem在评估系统和其他内在记忆方法中实现了领先的整体性能；在LongMemEval上的实验显示，即使支持证据已从当前上下文中移除，LiveMem仍能基于记忆状态回答问题，且证据距离分析表明，有用信息在活跃窗口之外仍能持续存在。因此，LiveMem将状态连续性确立为持续大语言模型推理的一种独特且互补的抽象概念。
英文摘要
Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retrieval preserve access to selected history, but do not provide a persistent state over the full lifecycle when working context changes. We formulate this missing inference capability as \emph{state continuity under context turnover}: carrying computation forward through a fixed-capacity memory state whose lifetime is independent of the active context. We introduce an intrinsic memory method, \textbf{LiveMem}, which augments a pretrained full-attention LLM with a memory state that preserves the historical information over the whole lifecycle while the main attention path retains a bounded KV window. Context turnover and memory state maintaining, memory-oriented post-training, and state-aware serving jointly make this memory state load bearing after its originating tokens are released. Our experiments show that LiveMem achieves leading overall performance among evaluated systems and other intrinsic memory methods. Experiments on LongMemEval show that LiveMem is able to answer the question based on the memory state, even when the supporting evidence has been removed from the current context, and evidence-distance analysis shows that useful information persists beyond the active window. LiveMem thus establishes state continuity as a distinct and complementary abstraction for continual LLM inference.
