Unverified50% confidenceFactExact time
Behind a tool call is a multi-round loop: the model first returns a tool call request rather than a final answer; the program executes the corresponding function, appends the return value as a tool result message to the conversation history, and requests the model again; the model decides based on the result whether to keep calling other tools or give a natural language answer, possibly repeating multiple times until the final answer is output.
1
Sources
50%
Confidence
Long-term
Relevance
11/8/2026
First Seen
Sources
Give Your AI Agent Its First Tool: A Calendar Query Walkthrough
youtubeAgent Lab AI11/6/2026
Related Entities
Related Claims
UnverifiedWhen the model requests a tool call, the finish_reason field in the response has the value tool_calls rather than stop, which is the standard signal for determining whether the model is requesting a tool call.76% similarUnverifiedAsynchronous tool calls allow the model to continue processing other logic while waiting for a tool to return results, without blocking the entire inference pipeline.75% similarUnverified传统ReAct框架要求模型在每次工具调用后将结果写回上下文再重新读取整个对话历史决定下一步,导致Token消耗和延迟累积74% similarUnverifiedThe ReAct pattern interweaves the language model's reasoning (Chain-of-Thought) with action calls to external tools within the same loop73% similarVerifiedA reasoning stream refers to the model's output of its thinking process before giving a final answer, which is returned incrementally (as deltas) during streaming and is typically interleaved with tool calls.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1148232API
curl https://kongchang.com/api/v1/knowledge/claims/1148232MCP
get_claim(id=1148232)