发表机构
Rutgers University; University of Pittsburgh; NEC Labs America; University of Maryland（罗格斯大学; 匹兹堡大学; NEC美国实验室; 马里兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OOPMAS提出无需训练的面向对象多智能体框架，按查询粒度生成智能体与工作流，利用动态技能库实现上下文改进，在混合任务上以89.6%准确率领先基线18.1个百分点。
AI 中文摘要
由大型语言模型驱动的多智能体系统（MAS）在代码生成、数学推理和问答方面表现出强劲性能。然而，现有的自动化MAS设计方法大多在任务级别运作，为每个基准生成一个固定的工作流，并统一应用于所有查询。这种假设在现实条件下不成立。任务内的查询难度差异很大，现实工作负载混合了异构的任务类型。我们引入了OOPMAS，一个无需训练的框架，在单个查询的粒度上生成智能体集合和协调工作流。智能体被表示为面向对象的类定义，具有专门的职责、工具和持久状态，工作流则表示为这些智能体对象上的可执行主函数。一个动态技能库从跨优化轮次的执行反馈中积累结构化经验，使得无需任何梯度更新或微调即可实现上下文内改进。在一个包含代码、数学和问答查询的混合任务基准上，OOPMAS达到了89.6%的准确率，比最强基线高出18.1个百分点。一项跨四个LLM骨干的模型替换研究显示出一致的扩展性，在最强模型上达到92.4%的准确率。
英文摘要
Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question answering. However, existing methods for automating MAS design mostly operate at the task level, producing a single fixed workflow per benchmark that is applied uniformly to all queries. This assumption fails under realistic conditions. Query difficulty varies widely within a task, and real-world workloads mix heterogeneous task types. We introduce OOPMAS, a training-free framework that generates both the agent set and the coordination workflow at the granularity of individual queries. Agents are represented as object-oriented class definitions with dedicated roles, tools, and persistent state, and workflows are expressed as executable main functions over these agent objects. A dynamic skill library accumulates structured lessons from execution feedback across optimization rounds, enabling in-context improvement without any gradient updates or fine-tuning. On a mixed-task benchmark of queries spanning code, math, and QA, OOPMAS achieves 89.6% accuracy, outperforming the strongest baseline by 18.1 percentage points. A model-swap study across four LLM backbones shows consistent scaling, reaching 92.4% with the strongest model.
