Unverified50% confidenceOpinionExact time
Existing skill-augmented generation methods typically separate skill retrieval from skill utilization, handling them with independent models, so the two processes cannot be optimized jointly.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedSkill分为能力型Skill和偏好型Skill，能力型随模型变强会被淘汰，偏好型更持久需要用评估保护防止性能倒退77% similarVerifiedWhen a skill description is so detailed that it contains all the information needed to complete a task, the model will skip the skill-calling step.77% similarUnverifiedIt is not advisable to install too many skills, as having too many can lead to erroneous triggering that affects results; greater emphasis should be placed on distilling one's own usage experience into dedicated skills.76% similarUnverifiedSkill filtering is not an optimization option, but a necessary mechanism for stable co-evolution.75% similarUnverifiedThe contributions between stages cannot be simply decomposed, and the objectives of different stages may conflict, causing the model to lose old knowledge while acquiring new skills.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114750API
curl https://kongchang.com/api/v1/knowledge/claims/1114750MCP
get_claim(id=1114750)