SOURCE-LINKED INTELLIGENCE

Same Model, Different Harness: Different Coding-Agent Results

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether changing the harness changes the result when the model and task stay fixed. We compare two configurations of the same harness on three coding benchmarks. The control supplies the full conversation in time order, while the treatment keeps the same record but mechanically shortens older tool results as the context fills and responds to repeated or stalled work. Under tight context, the treatment raises mean per-task fail-to-pass fraction (F2PF) in

Read original source ↗ Open in workspace

recordType

paper

region

Global