specific method · filed under inference & serving
Keep-recent-k
A context-management strategy that retains a recent portion of the context; the evidence does not specify the value of k.
Also called keep-recent-k context management, Keep-recent-k strategy.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
we employ a simple Keep-recent-k strategy
usedinference servingin GLM-5Z.ai
Filed alongside
Other methods under inference & serving :: context management.
Discard-all context managementPreserved thinking history modeExcluding prior thinking from conversation historyContext compactionContext foldingDiscard-75%Preserve thinkingThinking context management for tool useTrajectory summarization and rollout re-initiationContext management methodContext management strategyDiscarding tool-call historyHierarchical context managementMemory compressionModality-specific deploymentSummary-based context compressionTest-time context management for extending token budgets