自然语言智能体驱动

摘要

智能体性能日益依赖于架构工程，然而架构设计通常深嵌于控制器代码与运行时特定规范中，难以作为科学对象进行迁移、比较和研究。我们提出：能否将智能体架构的高层控制逻辑外化为可移植的可执行载体？我们引入自然语言智能体架构（NLAH），通过可编辑的自然语言描述架构行为，并开发智能架构运行时（IHR）——一个通过显式契约、持久化载体和轻量适配器执行这些架构的共享运行时环境。在编程与计算机操作基准测试中，我们通过可控实验评估了操作可行性、模块消融以及代码到文本的架构迁移能力。

English

Agent performance increasingly depends on harness engineering, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We introduce Natural-Language Agent Harnesses (NLAHs), which express harness behavior in editable natural language, and Intelligent Harness Runtime (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.