Handover of In-Context Learning State Across Session Boundaries
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Exploring continual learning without replay buffers: Our findings using dynamic task-similarity routing [P] →
- PossiblePossibly related (embedding) · 46%Show HN: ContextVault – Shared memory layer for your AI and your team →
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Handover of In-Context Learning State Across Session Boundar” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Masahiro Kato →
“Handover of In-Context Learning State Across Session Boundaries”
- LinkedLinked via arxiv author · 85%Taka Kato →
“Handover of In-Context Learning State Across Session Boundaries”