Complex agent harnesses don't improve code accuracy but can triple inference costs
Original article in Korean"성능은 그대로, 비용은 최대 3배"…에이전트 가로막는 '복잡한 하네스'
- Outlet
- AI Times
- Published
- Importance
- 3/5
Summary
Researchers from Shandong University and UC Berkeley report that adding tools and procedural complexity to AI coding agents does not meaningfully improve accuracy but can increase inference costs by up to 3x. They tested Anthropic's Claude Code, the open-source OpenCode, and a minimal configuration of mini-SWE-agent, finding that reducing unnecessary instructions and tool definitions has greater impact on cost efficiency.