New arXiv Paper Empirically Studies How Harness Design Shapes Coding Agent Performance
wek · hn · 2026-09-18
An arXiv paper presents an empirical study of harness design for coding agents — the scaffolding, tool interfaces, and prompt orchestration wrapped around models — and is drawing discussion on Hacker News.
The core question it tackles: the same model can perform very differently under different harnesses, making harness design an underappreciated variable in agent benchmarks and deployments.
More from coding & agent
- Butterfly traces multi-agent failures with graphs, 62.5% accuracy vs 53.8% for log prompting — JeremyCMorgan · 2026-11-04
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- Quota reset night: Codex back to 100% while Claude shows just 10% left — rudrank · 2026-11-04
- Self-improving software is inevitable: closing the agent-observability loop — bibryam · 2026-11-04
- Building a 7-GPU 132GB VRAM local inference rig: consolidate on EPYC or split across two systems? — infectiousstupidity · 2026-11-04
- Founder of 50-person, 12-country team says he talks to AI agents more than humans — Scobleizer · 2026-11-04