Blogs
Welcome to my technical blog. Here I share my thoughts and research on AI, Agents, and more.
What Is Actually Evolving in a Self-Evolving Agent?
What self-evolving agents actually repair, why completion alone can mislead selection, and when joint objectives, constraints and Pareto archives become usef...
What Makes a Benchmark Worth Testing?
How case construction shapes scores, what a smaller test set preserves, and how to build evidence for the decisions we actually care about. English / 中文.
When the Model Changes, What Happens to the Agent?
Why an agent tuned for one model can change behavior on another, and how to measure, adapt, and validate a model migration. English / 中文.