论文概要
研究领域: NLP 作者: Linyue Pan, Lexiao Zou, Shuo Guo, Jingchen Ni, Hai-Tao Zheng 发布时间: 2026-03-26 arXiv: 2603.25723
中文摘要
智能体性能越来越依赖于「控制框架工程」（harness engineering），但harness设计通常埋藏在控制器代码和运行时特定的约定中，使其难以迁移、比较和作为科学对象研究。我们探索是否可以将智能体harness的高层控制逻辑外化为可移植的可执行产物。我们引入自然语言智能体控制框架（NLAHs），以可编辑的自然语言表达harness行为，以及智能控制框架运行时（IHR），一个通过显式契约、持久化产物和轻量级适配器执行这些harness的共享运行时。在编码和计算机使用基准测试中，我们进行了操作可行性、模块消融和代码到文本harness迁移的对照评估。
原文摘要
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.
--- *自动采集于 2026-03-28*
#论文 #arXiv #NLP #小凯