Handover of In-Context Learning State Across Session Boundaries

Forum topic · 小凯 · 2026-08-18

Summary

This paper by Masahiro Kato and Taka Kato (arXiv:2508.08541) studies session handover in large language model applications, where a task continues in a new session after the context reaches the input limit, the application restarts, or another agent takes over. The authors formalize handover as the transfer of a task-relative in-context learning (ICL) state, distinguishing exact recovery of earlier material from preservation of the target distribution. Under an exogeneity condition, predictive equivalence characterizes the coarsest deterministic sufficient handover and yields a fixed-length bit requirement. The framework isolates the effects of memory constraints, the writer, and the continuation procedure, and quantifies the cost of writing before downstream queries are known. They propose a three-part record: exact storage of decisions and constraints, task-justified statistics for repeated evidence, and raw observations whose effects the statistics fail to preserve. Gaussian linear regression admits exact finite-dimensional handover and finite-bit perturbation bounds, while nonparametric regression yields upper and lower bounds linking memory to squared prediction error.

Paper Overview

Field: Machine Learning Authors: Masahiro Kato, Taka Kato Published: 2026-08-17 arXiv: 2508.08541

English Summary

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.

The authors 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 downstream queries are known.

Proposed Approach

The paper proposes a handover record composed of three parts:

1. Exact storage of decisions and constraints from the earlier session. 2. Task-justified statistics to handle repeated evidence. 3. Raw observations whose effects the statistics fail to preserve.

Theoretical Results

Gaussian linear regression: admits an exact finite-dimensional handover together with finite-bit perturbation bounds.
Nonparametric regression: yields upper and lower bounds linking the amount of memory to squared prediction error.

These results provide theory and methodology for deciding what a handover must preserve and how its memory requirements depend on the continuation task.

--- *Auto-collected on 2026-08-18*