Unverified50% confidenceFactExact time
Under a sampling strategy with a temperature parameter greater than 0, even if the input is exactly the same, a large model may produce different token sequences across multiple runs, thereby following different tool-calling paths and reasoning processes.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe tool selection behavior of large models is not entirely deterministic; under different temperature parameters, context lengths, or system prompts, the model may make different tool-calling decisions for the same problem.79% similarVerifiedThe temperature parameter design in the language model sampling process means that the same prompt may produce completely different outputs across different calls, so retrying itself does not guarantee convergence.77% similarVerifiedThe output of large language models is inherently probabilistic, and parameters such as sampling temperature and Top-P mean the model may generate different content each time, posing a challenge for software testing.77% similarVerifiedWhen a large language model generates each token, it samples from a probability distribution; the temperature parameter controls the degree of randomness—higher temperature produces more diverse outputs, while lower temperature produces more deterministic ones.76% similarUnverified温度参数T趋近于0时模型趋向贪心解码，相同输入下必然给出完全相同输出，是导致Agent固化循环的根本原因75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036717API
curl https://kongchang.com/api/v1/knowledge/claims/1036717MCP
get_claim(id=1036717)