Kaiyan Zhang (张开颜)

Project lead and corresponding author for the Self-Improving Agents survey. Homepage identifies Kaiyan Zhang as a final-year Tsinghua PhD candidate advised by Bowen Zhou, links Google Scholar, GitHub iseesaw, and X OkhayIea; OpenReview profile records Frontis.AI principal researcher from 2026 and Tsinghua PhD history.

1 archived notes X: high Homepage GitHub X

Jun 28, 2026

Self Improving Agents in the Era of Experience: A Survey of Self to Meta Evolution

这篇 survey 把 self improving agents 从模型自我训练扩展为部署后 runtime system 的 trace to capability 问题：harness 将交互 trace 编译成可验证 experience，再分别写入 skills、memory、environment/tool boundary、model parameters 或 meta layer。它的主要贡献是给 self impro...

2026-06-25-self-improving-agents-era-experience-survey Agent RL Agent Memory Agent Workflow

Related Notes

Self Improving Agents in the Era of Experience: A Survey of Self to Meta Evolution