自然語言智慧體驅動系統

摘要

代理效能的提升日益依賴於框架工程的優化，然而框架設計通常深嵌於控制器代碼與運行時特定規範中，難以作為科學研究對象進行遷移、比較和分析。我們提出一種創新思路：能否將代理框架的高階控制邏輯外部化為可移植的執行載體？為此我們引入自然語言代理框架（NLAH），通過可編輯的自然語言表述框架行為，並設計智能框架運行時（IHR）作為共享執行環境，通過明確定義的契約、持久化載體與輕量適配器實現框架運作。在編程與計算機操作基準測試中，我們針對運行可行性、模塊消融實驗以及代碼到文本的框架遷移開展了對照評估。

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.