让大模型自动搭建智能体，自动生成结构和工具。
OpenSage: Self-programming Agent Generation Engine
- 用大模型自动生成智能体的结构与工具集。
- 在多个基准上性能超越现有开发框架。
- 适合研究AI自主开发智能体的团队使用。
智能体开发工具包（ADK）为构建智能体提供了有效平台和工具，其设计对智能体性能至关重要，尤其体现在智能体拓扑、工具和记忆功能方面。然而，当前ADK或功能不足，或依赖人工设计组件，限制了智能体的泛化能力和整体表现。我们提出OpenSage，首个实现大模型自动创建具有自生成拓扑和工具集的智能体的ADK，同时提供全面且结构化的记忆支持。OpenSage使智能体能自主创建和管理子智能体与工具集，并采用分层图结构记忆系统实现高效管理，还配备针对软件工程任务优化的专用工具集。在三个前沿基准上，使用多种骨干模型进行的广泛实验验证了OpenSage相对于现有ADK的优势。严谨的消融实验进一步证明了各组件设计的有效性。我们认为，OpenSage将推动下一代智能体开发，实现从以人为核心向以AI为核心的范式转变。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。