Gaotang Li, Bhavana Dalvi Mishra, Yifei Ming, Yanfei Chen, Zhongying CuiZhu, Lesly Miculicich, Long Tan Le, Rui Meng, Chun-Liang Li, Hanghang Tong, Chen-Yu Lee, Tomas Pfister · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28380 · cited by 0 works (OpenAlex) · open-access PDF
在这项工作中,我们引入了对象导向(OO-Harness),一种的优化框架,通过使用对象导向设计来发展可执行类的层次结构。在训练过程中,一个进化代理使用执行记录来创建一个专门的家族,每一个以基础的子类或通过继承的现有专门的形式实施。在测试时,路由器使用在训练期间积累的路由器更少来选择每个任务的特性。在跨越三个长视野的基准,涵盖业务流程,工作空间任务和工具,使用 OO-Harness实现了与方法相比的最佳性能,在其核心组件的扩展研究中增加了15%的绝对提高。
Machine translation (Meta M2M100); the English original follows.
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different execution strategies. In this work, we introduce Object-Oriented Harness (OO-Harness), a harness optimization framework that evolves a hierarchy of executable harness classes using object-oriented design. During training, an evolution agent uses execution records to create a family of specialized harnesses, each implemented as a subclass of the base or an existing specialized harness via inheritance. At test time, a harness router uses routing lessons accumulated during training to select a specific harness for each task. Across three long-horizon benchmarks spanning business workflows, workspace tasks, and tool use, OO-Harness achieves the best performance among the compared methods, with an absolute improvement of up to 15% over the base. Extensive ablation studies examine the contributions of its core components.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Executable, Computer science, Hierarchy, Distributed computing, Workspace, Control flow
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28380, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange