Harness-of-Harness framework boosts autonomous coding agents by 52% over multi-day runs

rohanpaul_ai · x · 2026-09-06

An arXiv paper introduces Harness-of-Harness (HoH), a framework that lets LLM coding agents autonomously develop and continually improve software over multi-day runs without human intervention.

The core argument: long-horizon coding needs persistent project state, independent testing, and replanning from real failures—not just more time.

Related event: Shanghai AI Lab's Harness-of-Harness Boosts Long-Horizon Coding Agents by 52%(4 posts)→

Original post →

More from coding & agent

coding & agent channel →