# AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol

arXiv: https://arxiv.org/abs/2506.12508 · HTML: https://mlsanity.com/paper/2506.12508/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 15 of 15)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Cradle: Empowering Foundation Agents Towards General Computer Control](https://mlsanity.com/paper/2403.03186/) (2024)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent](https://mlsanity.com/paper/2505.02024/) (2025)
- [SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems](https://mlsanity.com/paper/2506.07564/) (2025)
- [LLM-Powered AI Agent Systems and Their Applications in Industry](https://mlsanity.com/paper/2505.16120/) (2025)

## Built on by (most cited first, 30 of 39)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025)
- [Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation](https://mlsanity.com/paper/2510.11977/) (2025)
- [FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction](https://mlsanity.com/paper/2508.11987/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents](https://mlsanity.com/paper/2509.06283/) (2025)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning](https://mlsanity.com/paper/2509.21193/) (2025)
- [A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks](https://mlsanity.com/paper/2511.00872/) (2025)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges](https://mlsanity.com/paper/2510.09404/) (2025)
- [HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application](https://mlsanity.com/paper/2510.19631/) (2025)
- [TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data](https://mlsanity.com/paper/2511.02219/) (2025)
- [MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning](https://mlsanity.com/paper/2601.19204/) (2026)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving](https://mlsanity.com/paper/2605.22566/) (2026)
- [Multi-Agent Computer Use](https://mlsanity.com/paper/2606.01533/) (2026)
- [Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering](https://mlsanity.com/paper/2607.25090/) (2026)
- [Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems](https://mlsanity.com/paper/2603.20578/) (2026)
- [Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestration](https://mlsanity.com/paper/2604.07911/) (2026)
- [EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools](https://mlsanity.com/paper/2604.07927/) (2026)
- [From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company](https://mlsanity.com/paper/2604.22446/) (2026)
- [Heterogeneous Scientific Foundation Model Collaboration](https://mlsanity.com/paper/2604.27351/) (2026)
- [EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems](https://mlsanity.com/paper/2606.18668/) (2026)
- [ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents](https://mlsanity.com/paper/2606.31174/) (2026)
- [Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis](https://mlsanity.com/paper/2607.20216/) (2026)
- [Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning](https://mlsanity.com/paper/2609.38147/) (2026)

## Abstract (arXiv)

Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-aware coordination across agents, tools, and environments. To address this limitation, we introduce the Tool-Environment-Agent (TEA) protocol, a unified abstraction that models these components as first-class, versioned resources with explicit lifecycles. TEA supports end-to-end context and version management, improving traceability and reproducibility, while also enabling continual self-evolution of agent-associated componentsfootnoteUnless otherwise specified, agent-associated components include prompts, memory/tool/agent/environment code, and agent outputs (solutions).. Building on TEA, we present projectname, a hierarchical multi-agent framework in which a central planner coordinates specialized sub-agents and dynamically extends capabilities during execution. Experiments on four challenging benchmarks, spanning expert-level agent tasks and scientific/mathematical reasoning, show that AgentOrchestra consistently outperforms strong baselines; in particular, it achieves 89.04% on the GAIA Test set, placing it among the leading methods to the best of our knowledge. These results highlight the value of explicit protocol design and hierarchical orchestration for building more robust and adaptive multi-agent systems.