Unverified50% confidenceFactExact time
When multiple tools are semantically similar, the model's tool selection is essentially a multi-class classification problem, and the more candidate classes there are, the higher the misclassification rate.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen multiple algorithms with different inductive biases all converge on the same error pattern, it indicates that the problem lies at the level of problem definition or the feature space rather than the models themselves.72% similarUnverifiedIf the data always provides tools that get used, the model learns the erroneous association that it must use a tool whenever it sees one.72% similarUnverifiedIf only the data of newly added classes is used to fine-tune an expanded classification head, the model is highly prone to catastrophic forgetting, rapidly losing its ability to recognize the original classes.69% similarUnverifiedInference methods based on model internal features face a trade-off between false positives and false negatives69% similarUnverifiedIn Agentic scenarios, sources of error may include prompt design flaws, tool API return formats not matching expectations, information loss during multi-step reasoning, or gaps in the model's domain knowledge.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/932580API
curl https://kongchang.com/api/v1/knowledge/claims/932580MCP
get_claim(id=932580)