Self-Harness Lets Agents Modify Their Own Harness

量子位 · wechat · 2026-07-18

The Shanghai Artificial Intelligence Laboratory proposed Self-Harness: a method allowing models to automatically mine failure modes from their harness based on execution trajectories, propose constrained modifications, and decide whether to adopt them via regression testing.

The core workflow has three steps:

The paper evaluates this on Terminal-Bench-2.0, keeping the model, tool environment, and evaluation protocol fixed while only altering the outer Harness. All three backends saw improvements:

The authors observed that different models have distinct weaknesses: some delay output generation, others get stuck in loops after tool failures, and some need tighter control over shell state transitions. This proves Self-Harness isn't just adding a generic prompt, but integrating the model into an engineering loop of "finding issues, proposing fixes, and validating them."

Related event: Agent Harness Self-Improvement and Domain-Specific Design(6 posts)→

Original post →

More from coding & agent

coding & agent channel →