Unverified50% confidenceFactExact time
Sub-agents independently select models based on their own assessment of subtask complexity rather than inheriting the model setting of the main session, which causes multiple models that the user never manually selected to appear in usage reports.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedModel selection should involve running the same set of representative use cases through different candidate models, comparing classification accuracy, recall on sensitive cases, latency, and cost, with decisions made by evaluation rather than by model labels74% similarUnverifiedGenerative decision models must process the current context together with all candidate options on every call, with the computational load increasing as the number of options grows.74% similarUnverifiedSkills 机制通过上下文注入在不修改模型权重的前提下引导模型输出，相比一次性 Prompt Engineering 强调可复用性、版本管理和模块化组合73% similarUnverifiedThere are two paths to getting the model to output an accurate solution: writing detailed requirements all at once, or using follow-up questioning to have the model think on the user's behalf and accumulate context.73% similarUnverifiedThe non-interactive paradigm allows multiple heterogeneous SLMs to independently generate candidate solutions, after which a router orchestrates these cached samples without requiring further interaction between models72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978583API
curl https://kongchang.com/api/v1/knowledge/claims/978583MCP
get_claim(id=978583)