Research · Agents
Joint harness search balances model accuracy, safety, and token use
MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
Across 17 domains and 12 models, jointly optimizing the code around language models outperformed sequential and accuracy-only approaches.
3D hypervolume: 0.48 hypervolume indicator (as reported)
Adobe Research