Author

Yan-Fei Zhang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Nov 2026

Artifact-to-Capability: Diagnosing Breaks in Capability Formation of Self-Evolving Agents in a Controlled Environment

This work defines capability formation from artifacts as five sequentially dependent properties, two of which form a checkpoint for capability formation, and introduces three-scale diagnosis, which judges these properties at the state, game, and lineage levels.

Zi-Qian Ban, Hao-Xiang Yang, Yan-Fei Zhang et al. · 0 citations

#artificial intelligence Preprint Sep 2026

After the Fix: Transfer of Corrected Agent Experience

This work transfers the same failed source before and after accepted repair to a fixed target, alongside independent execution, alongside independent execution in the ThinkingBox and APEX regimes to establish comparable aggregate correction benefits.

Yan-Fei Zhang, Xue-Min Lin · 0 citations