arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16891cs.AIcs.CRcs.SE
收藏

OpenSage:自主编程代理生成引擎

OpenSage: Self-programming Agent Generation Engine

Hongwei Li, Zhun Wang, Qinrun Dai, Yuzhou Nie, Jinjun Peng, Ruitong Liu, Jingyang Zhang, Kaijie Zhu, Jingxuan He, Lun Wang, Yangruibo Ding, Yueqi Chen, Wenbo Guo, Dawn Song

AI总结:

OpenSage是首个允许大语言模型自动创建代理的ADK,提供结构化内存支持和自动生成拓扑与工具集,通过实验验证其在代理开发中的优势。

摘要:

代理开发套件(ADKs)为构建代理提供了有效平台和工具,其设计对代理性能至关重要,尤其是代理拓扑、工具和内存功能。然而,当前ADKs要么缺乏足够的功能支持,要么依赖人类手动设计这些组件,限制了代理的泛化能力和整体性能。我们提出了OpenSage,首个允许LLM自动创建代理的ADK,代理可自主生成拓扑和工具集,并提供全面的结构化内存支持。OpenSage为代理提供创建和管理子代理和工具集的有效功能,还包含一种分层、基于图的内存系统以实现高效管理,以及专为软件工程任务定制的工具包。在三个最先进的基准测试中,使用各种主干模型进行的广泛实验展示了OpenSage相较于现有ADKs的优势。我们还进行了严格的消融研究,以证明我们的设计对每个组件的有效性。我们相信OpenSage可以为下一代代理开发铺平道路,从以人类为中心转向以AI为中心的范式。

英文摘要:

Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory. However, current ADKs either lack sufficient functional support or rely on humans to manually design these components, limiting agents' generalizability and overall performance. We propose OpenSage, the first ADK that enables LLMs to automatically create agents with self-generated topology and toolsets while providing comprehensive and structured memory support. OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits. It also features a hierarchical, graph-based memory system for efficient management and a specialized toolkit tailored to software engineering tasks. Extensive experiments across three state-of-the-art benchmarks with various backbone models demonstrate the advantages of OpenSage over existing ADKs. We also conduct rigorous ablation studies to demonstrate the effectiveness of our design for each component. We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑