Unverified50% confidenceFactExact time
The model itself has no built-in judgment of "I'm done"; it merely predicts the next token at each step, and without an explicit termination signal the model tends to keep calling tools.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
Unverified传统自回归推理中，模型每一步只能基于已有上下文预测下一个token，是串行依赖关系74% similarUnverifiedNative agents typically have the model itself decide the next action (ReAct pattern), with the execution path dynamically generated at runtime and impossible to verify in advance.73% similarUnverifiedA single model itself has no persistent goals, but once connected to tool calling, memory and a looped decision-making framework, it exhibits clear agentic characteristics.73% similarUnverifiedWhen models are exposed to the complete timeline, they exhibit stable, hindsight-sensitive answer shifts, tending to provide answers consistent with known outcomes but not reasonable at the decision point.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092814API
curl https://kongchang.com/api/v1/knowledge/claims/1092814MCP
get_claim(id=1092814)