• Homepage
  • About Me
  • News
  • Publications
  • Blog
  • Honors and Awards
  • Educations
  • Invited Talks
  • Internships
    Shi Qiu

    Shi Qiu

    Peking University

    • Shi Qiu's Homepage
    • Beijing, China
    • Email
    • ResearchGate
    • Github
    • Google Scholar
    • ORCID

    ✍️ Blog

    Notes on agent harnesses — the scaffolding around models that decides whether an autonomous agent thinks or collapses. Context engineering, tool design, verification loops, and lessons from building self-evolving research agents.

    Verification Loops: Why Self-Evolving Agents Need Adversarial Critics
    Jul 4, 2026 ·agents

    Verification Loops: Why Self-Evolving Agents Need Adversarial Critics

    An agent that grades its own work grades it too kindly. The single highest-leverage pattern I've found for autonomous research agents is a separate, adversarial verifier whose j...

    Read more →
    Tools Are the API Your Agent Actually Sees
    Jun 28, 2026 ·agents

    Tools Are the API Your Agent Actually Sees

    You can't prompt your way out of a bad tool interface. The set of tools you hand an agent — their names, their granularity, their error messages — shapes its behavior more than ...

    Read more →
    Context Is the Real Budget: Notes on Engineering Agent Harnesses
    Jun 20, 2026 ·agents

    Context Is the Real Budget: Notes on Engineering Agent Harnesses

    The model is rarely the bottleneck. After a year of building self-evolving research agents, the thing that decides whether an agent succeeds or collapses is how its harness spen...

    Read more →