general family · filed under inference & serving
Test-time context management for extending token budgets
A broad description of using context management to extend token budgets at test time, without specifying a particular mechanism.
- 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.
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 managementKeep-recent-kMemory compressionModality-specific deploymentSummary-based context compression