Unverified90% confidenceFactTime unknown
在Agent Scratchpad中，LLM生成的工具调用作为AI Message存储，工具返回的结果作为Tool Message存储，两者通过tool_call_id进行关联
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
LangChain Agent Executor Architecture: Building a ReAct Agent from Scratch
youtubeJames Briggs
Related Entities
Related Claims
UnverifiedWhen an LLM model decides to call a tool, it generates an assistant message containing a tool_use block; after the tool finishes executing, the result is appended as a new message in tool_result format73% similarUnverified在LangChain框架中，Tool调用结果通过ToolMessage对象追加到消息链68% similarUnverifiedHarness在转接过程中会预置系统提示词（system prompt），即便用户未写提示词，AI仍知道自己的身份65% similarUnverifiedThe dynamic tool mechanism allows agents to add or remove available tools in real time based on task progress during execution.65% similarUnverifiedAnthropic's Messages API passes the system message as a separate top-level parameter rather than placing it in the messages array; tool calls use the tool_use and tool_result content block types.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16130API
curl https://kongchang.com/api/v1/knowledge/claims/16130MCP
get_claim(id=16130)