Recent advances in LLM-based agent systems have shown promise in tackling complex, long-horizon tasks. However, existing LLM-based agentprotocols (e.g., A2A and MCP) under-specify cross-entity lifecycle and context management, version tracking, and ad-hoc environment integration, which in turn encourages fixed, monolithic agent compositions and brittle glue code. To address these limitations, we introduce the Tool-Environment-Agent (TEA) protocol, a unified abstraction that models environments, agents, and tools as first-class resources with explicit lifecycles and versioned interfaces. TEA provides a principled foundation for end-to-end lifecycle and version management, and for associating each run with its context and outputs across components, improving traceability and reproducibility. Moreover, TEA enables continual self-evolution of agent-associated components through a closed feedback loop, producing improved versions while supporting version selection and rollback. Building on TEA, we present AgentOrchestra, a hierarchical multi-agent framework in which a central planner orchestrates specialized sub-agents for web navigation, data analysis, and file operations, and supports continual adaptation by dynamically instantiating, retrieving, and refining tools online during execution. We evaluate AgentOrchestra on three challenging benchmarks, where it consistently outperforms strong baselines and achieves 89.04% on GAIA, establishing state-of-the-art performance to the best of our knowledge. Overall, our results provide evidence that TEA and hierarchical orchestration improve scalability and generality in multi-agent systems.

翻译：基于大语言模型的智能体系统近期在应对复杂、长周期任务方面展现出潜力。然而，现有基于大语言模型的智能体协议（如A2A与MCP）在跨实体生命周期与上下文管理、版本追踪以及临时环境集成方面存在规范不足的问题，这导致了固定、单一化的智能体组合与脆弱的胶合代码。为应对这些局限，我们提出了工具-环境-智能体（TEA）协议，该协议通过统一抽象将环境、智能体与工具建模为具有显式生命周期和版本化接口的一等资源。TEA为端到端的生命周期与版本管理提供了原则性基础，并支持将每次运行与其跨组件的上下文及输出相关联，从而提升了可追溯性与可复现性。此外，TEA通过闭环反馈机制实现了智能体关联组件的持续自我进化，能够生成改进版本，同时支持版本选择与回滚。基于TEA协议，我们提出了AgentOrchestra——一个层次化多智能体框架，其中央规划器负责协调专用于网络导航、数据分析和文件操作的子智能体，并通过在执行过程中动态实例化、检索与在线优化工具来支持持续自适应。我们在三个具有挑战性的基准测试上对AgentOrchestra进行了评估，其表现始终优于现有强基线模型，并在GAIA基准上达到89.04%的准确率，据我们所知，这代表了当前最优性能。总体而言，我们的研究结果表明，TEA协议与层次化编排机制能够有效提升多智能体系统的可扩展性与泛化能力。