ambiguous · filed under inference & serving
Context management strategy
A strategy used with a 300,000-token context limit, with no further mechanism specified in the evidence.
- 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.
The evaluation is conducted with a maximum context length of 300,000 tokens, using a context management strategy.
usedunclearin GLM-5.3Z.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 methodDiscarding tool-call historyHierarchical context managementKeep-recent-kMemory compressionModality-specific deploymentSummary-based context compressionTest-time context management for extending token budgets