这篇论文戳中了AI智能体工程化的核心痛点——控制层设计比模型选择更关键，做智能体框架或复杂任务自动化的开发者值得一读。
一篇新论文指出，AI智能体的真实行为更多来自其外围的“控制层”（harness），而非模型本身或提示词。该控制层负责规划、工具调用、记忆、重试、验证和停止等逻辑，而许多智能体将这一层隐藏在代码中，导致问题难以调试。论文提出“自然语言智能体控制层”概念，用结构化自然语言表达这些逻辑，使其可检查、可移植、可测试。在SWE-bench上的实验表明，增加控制层结构会显著改变智能体行为，但并非总是带来性能提升。
This paper shows that agent performance depends le…
This paper shows that agent performance depends less on prompts alone and more on the harness around them.
“Agent intelligence” is becoming partly a systems problem. The problem is that many AI agents look like 1 model, but their real behavior comes from surrounding code that controls planning, tools, memory, retries, checking, and stopping.
A model may reason well in one step, but long tasks fail in messier places: state disappears, verification drifts, tools return partial evidence, and the agent forgets which intermediate artifact actually matters.
Natural-Language Agent Harnesses try to make that control layer visible.
Instead of burying the logic in controller code, they express the stages, roles, contracts, state rules, failure modes, and stopping conditions in structured natural language that a shared runtime can execute.
The claim is not that natural language should replace code, but that the important design choices around an agent should become inspectable, portable, and testable instead of hiding inside one framework’s habits.
On SWE-bench, heavier harnessing changed behavior dramatically, with more calls, tools, delegation, and runtime, but it did not produce a simple win curve; sometimes added structure helped, and sometimes it pushed the agent away from the shortest benchmark-aligned repair.
A harness is not magic scaffolding around a model; it is a set of bets about where reliability comes from.
----
Paper Link – arxiv. org/abs/2603.25723
Paper Title: "Natural-Language Agent Harnesses"