用模块化抽象让多智能体系统更易构建、观察和演化
OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
- 将智能体、工具、大模型等封装为可插拔组件，实现灵活组合
- 运行时生成动态执行图，支持自适应可视化与实时监控
- 内置自动进化引擎，支持数据回流与持续优化，适合工业级系统
在复杂工业环境中部署生产级多智能体系统（MAS）仍面临扩展性差、可观测性弱和自主演化能力不足的挑战。本文提出 OxyGent，一个开源框架，核心创新包括统一的 Oxy 抽象和 OxyBank 进化引擎。统一抽象将智能体、工具、大模型及推理流程封装为可插拔原子组件，实现类似积木的可扩展系统构建与非侵入式监控。为提升可观测性，OxyGent 引入权限驱动的动态规划，以运行时生成的执行图替代固定工作流，提供自适应可视化。此外，为支持持续演化，OxyBank 作为 AI 资产管理平台，驱动自动化数据回流、标注与联合进化。实证评估与真实案例表明，OxyGent 为 MAS 提供了稳健且可扩展的基础。项目已开源，许可协议为 Apache License 2.0，地址：https://github.com/jd-opensource/OxyGent。
原文摘要 · Abstract (English)
Deploying production-ready multi-agent systems (MAS) in complex industrial environments remains challenging due to limitations in scalability, observability, and autonomous evolution. We present OxyGent, an open-source framework driven by two core novelties: a unified Oxy abstraction and the OxyBank evolution engine. The unified abstraction encapsulates agents, tools, LLMs, and reasoning flows as pluggable atomic components, enabling Lego-like scalable system composition and non-intrusive monitoring. To enhance observability, OxyGent introduces permission-driven dynamic planning that replaces rigid workflows with execution graphs generated at runtime, providing adaptive visualizations. Furthermore, to support continuous evolution, OxyBank serves as an AI asset management platform that drives automated data backflow, annotation, and joint evolution. Empirical evaluations and real-world case studies show that OxyGent provides a robust and scalable foundation for MAS. OxyGent is fully open-sourced under the Apache License 2.0 at https://github.com/jd-opensource/OxyGent.
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。