A New Study Finally Tests the Guesswork Behind Coding Agents' 'Harness' Design
Nine researchers ran 176 controlled experiments on the scaffolding wrapped around coding agents, the part almost nobody measures, and found the fixes that actually work are duller than the ones that sound clever.
Everything this piece is built on.
- An Empirical Study of Harness Design for Coding AgentsARXIVORG
- An Empirical Study of Harness Design for Coding Agents (paper page)HUGGINGFACE
- Harness Engineering: Anatomy, Architecture, and Evolution of Coding AgentsARXIVORG
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent HarnessesARXIVORG
- The Interplay of Harness Design and Post-Training in LLM AgentsARXIVORG