Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
The results show that some search procedures can occasionally find large gains but still choose brittle updates, so the reliability of the chosen harness should be reported alongside average held-out lift, so the reliability of the chosen harness should be reported alongside average held-out lift.
Cen-Mia Zhao, Hai-Bo Ruan, Wen-Jie Chen et al.
· 4 citations
· ⚡1