Unverified50% confidenceFactExact time
The termination logic of an Agent Loop is to loop until the model no longer initiates any tool calls.
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe termination condition of an agentic loop typically falls into one of two categories: the model returns a plain-text response (stop_reason is end_turn), or the preset maximum number of iterations is reached.78% similarVerifiedCommon termination strategies for Agent Loop include three layers: semantic termination (such as detecting the Final Answer marker), an iteration limit (max_iterations typically defaults to 10–15), and timeout protection (the timeout parameter).78% similarUnverifiedAgent Loop的终止条件通常是LLM不再产生工具调用请求，或达到最大步骤限制（max_iterations）77% similarUnverified驱动Agent Loop循环的两个信号来自模型返回的stop_reason字段：当stop_reason等于tool_use时宿主执行工具并继续循环，否则循环退出75% similarUnverified在Agent Loop中如果只将工具结果塞回messages而漏掉assistant消息，模型会陷入无限循环，不断重复调用工具75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/993941API
curl https://kongchang.com/api/v1/knowledge/claims/993941MCP
get_claim(id=993941)