Model techniques map
Techniquesinference & servingcontext management

specific method · filed under inference & serving

Context folding

A strategy for long search-agent contexts that prunes earlier tool responses after their cumulative length reaches a preset threshold.

Also called context-folding strategy, simple context-folding strategy(256k).

sources
2
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

evaluated 1used 1

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

most search agents built on our model adopt a simple context-folding strategy(256k): once the cumulative Tool Response length reaches a preset threshold, earlier Tool Responses are pruned from the history to keep the context within limits.

usedinference serving

BrowseComp: we tested two strategies, simple context-folding achieved a score of 69.0

evaluatedinference servingin Qwen3.5-based search agentsQwen

Filed alongside

Other methods under inference & serving :: context management.