Unverified50% confidenceFactExact time
ViSkill is a vision-native skill learning framework that lets VLM agents encode successful interactions as composite visual skill cards, call them directly during inference and reward shaping, and through closed-loop feedback let the skill library and policy reinforce each other.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedA Skill is the concept of packaging multi-step interaction logic, context management, and output constraints into a callable unit, distinct from a single-interaction prompt template.65% similarUnverifiedSkill 开发涉及底层编码基础、对 AI 运作原理的理解、Prompt 工程技巧以及具体场景落地经验等多个层面的能力65% similarUnverifiedSkill本质是一套由提示词模板、参数配置和后处理规则组成的结构化工作流，样本视频被转化为风格向量或风格描述符存储在配置文件中65% similarUnverifiedVICO's co-evolution can be seen as a fusion of curriculum learning and self-play ideas in the vision-language modality, with the EnvRewriter playing the role of a teacher that dynamically generates questions based on the student's capability.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013368API
curl https://kongchang.com/api/v1/knowledge/claims/1013368MCP
get_claim(id=1013368)