A smaller model with the right task-specific harness can beat a stronger model.

New paper introduces JIT-Agent, which takes exactly this approach: it generates the agent harness on demand, choosing how memory, planning, actions, tools, and skills should work for the specific task.

DeepSeek-V4-Flash with JIT-Agent scored 85.1 on DeepSearchQA, versus 76.0 for GPT-5.6.

That change was enough to move the same backbones substantially. Across 18 matched backbone-benchmark pairs, every JIT-generated harness improved the underlying model; the 9-benchmark average rose by 7.7 points for GLM-5.2 and 8.8 for DeepSeek-V4-Flash.

This was not simply more inference. In controlled comparisons against fixed harnesses such as Claude Code, Codex, OpenCode, Hermes, and NanoBot, JIT-Agent had the lowest token use and API cost in all 6 settings, with 36.0% lower cost on average than the cheapest fixed alternative.

– arxiv. org/abs/2608.25593

Title: "JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution"