发表机构
Mizuho-DL Financial Technology; the University of Tokyo; RIKEN AIP; Osaka Metropolitan University（瑞穗数字金融科技; 东京大学; 理化学研究所人工智能项目; 大阪公立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对大语言模型应用的会话移交问题，提出三部分记录方法，结合高斯线性与非参数回归，为移交的信息保留及记忆需求提供理论与方法。
AI 中文摘要
本研究探讨使用大语言模型的应用中会话移交的方法论与理论特性。当上下文达到模型输入限制、应用重启，或要求其他智能体完成任务时，任务可在新会话中继续，此时应用必须决定传递前一会话的哪些信息。我们将移交建模为任务相关的上下文学习（ICL）状态的转移，并区分先前材料的精确恢复与目标分布的保留。在外生性条件下，预测等价性刻画了最粗略的确定性充分移交，并给出固定长度的比特需求。该分析分离了记忆约束、写入者及延续过程的影响，并量化了在实现的下游查询未知前进行写入的成本。我们提出一种三部分记录：精确存储决策与约束，使用任务合理的统计量处理重复证据，保留那些未被上述统计量保留其效应的原始观测值。高斯线性回归给出了精确的有限维移交与有限比特扰动界，而非参数回归则给出了关联记忆与平方预测误差的上下界。这些结果为决定移交必须保留的内容及其记忆需求如何依赖于延续任务提供了理论与方法。
英文摘要
This study investigates the methodological and theoretical properties of session handover in applications that use large language models. A task may continue in a new session when the context reaches the model's input limit, when the application restarts, or when another agent is asked to finish the task. The application must then decide which information from the earlier session to pass on. We formulate handover as the transfer of a task-relative in-context learning (ICL) state and distinguish exact recovery of earlier material from preservation of the target distribution. Under an exogeneity condition, predictive equivalence characterizes the coarsest deterministic sufficient handover and gives a fixed-length bit requirement. The analysis isolates the effects of the memory constraint, the writer, and the continuation procedure, and quantifies the cost of writing before the realized downstream query is known. We propose a three-part record that stores decisions and constraints exactly, uses task-justified statistics for repeated evidence, and retains original observations whose effect is not preserved by those statistics. Gaussian linear regression gives an exact finite-dimensional handover and finite-bit perturbation bounds, while nonparametric regression gives upper and lower bounds that relate memory to squared prediction error. These results provide a theory and method for deciding what a handover must retain and how its memory requirement depends on the continuation task.
