SOURCE-LINKED INTELLIGENCE

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current

Read original source ↗ Open in workspace

recordType

paper

region

Global