implementation detail · filed under inference & serving
Retaining chain-of-thought across tool-call turns
Previous chain-of-thought is passed back as input for subsequent sampling when tools are called within it.
- 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 exception for this is tool/function calling. The model is able to call tools as part of its chain-of-thought and because of that, we should pass the previous chain-of-thought back in as input for subsequent sampling.
usedinference servingin gpt-ossOpenAI
Filed alongside
Other methods under inference & serving :: agentic scaffolding.
Advisor strategyAutomatic tool choicePython toolFunction callingHarmony formatBrowser toolGeneric tool-call parserMCP tool configurationMulti-agent collaborationRole-based instruction hierarchyThinking with toolsVisual Search ToolXML-based tool-call schema with DSML tokenAgent Team modeAgentENVAgentic searchAgentic tool callingApp-server mode with adapted tool schemasAppArmor and eBPF sandbox policiesAssistant output channelsAsynchronous teammate spawningBash commands for context retrievalBash computer-use agentBrowsing tool with domain filtering