mlsanityData to 14 Oct 2026

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

arXiv 2506.12508 ↗First posted 14 Jun 2025cs.AIcited by 39

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

15 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution26 May
  2. 2025LLM-Powered AI Agent Systems and Their Applications in Industry22 May
  3. 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent4 May
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 11

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  3. 2016OpenAI Gymcited by 1,736
  4. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  5. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  6. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  7. 2025Humanity's Last Examcited by 491
  8. 2024Cradle: Empowering Foundation Agents Towards General Computer Controlcited by 117
  9. 2025A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)cited by 101
  10. 2025LLM Agents Making Agent Toolscited by 48
  11. 2025SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systemscited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 27.

39 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  3. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 95
  4. 2025Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluationcited by 92
  5. 2025FutureX: An Advanced Live Benchmark for LLM Agents in Future Predictioncited by 59
  6. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  7. 2025SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agentscited by 31
  8. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  9. 2025Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoningcited by 11
  10. 2025A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Taskscited by 7
  11. 2025Agentic Services Computingcited by 6
  12. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
27 more
  1. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  2. 2025Agentic Systems in Radiology: Design, Applications, Evaluation, and Challengescited by 5
  3. 2025HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Applicationcited by 5
  4. 2025TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Datacited by 5
  5. 2026MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoningcited by 3
  6. 2026Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Promptscited by 3
  7. 2026GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Servingcited by 3
  8. 2026Multi-Agent Computer Usecited by 3
  9. 2026Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineeringcited by 2
  10. 2026Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systemscited by 1
  11. 2026Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestrationcited by 1
  12. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Toolscited by 1
  13. 2026From Skills to Talent: Organising Heterogeneous Agents as a Real-World Companycited by 1
  14. 2026Heterogeneous Scientific Foundation Model Collaborationcited by 1
  15. 2026EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systemscited by 1
  16. 2026ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agentscited by 1
  17. 2026Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysiscited by 1
  18. 2026Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoningcited by 1
  19. 2026OctoNest: Adaptive Cross-Device Execution through Stateful Controlcited by 0
  20. 2026Unified Agent: Managing Interactions across Devicescited by 0
  21. 2026Testing and Evaluation of Agentic AI Systems In Military Command and Controlcited by 0
  22. 2026ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Researchcited by 0
  23. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0
  24. 2026ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Codingcited by 0
  25. 2026Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Executioncited by 0
  26. 2026WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestrationcited by 0
  27. 2026Incremental Open-Ended Deep Research with Structured Harnesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
  2. 2025SynthTools: A Framework for Scaling Synthetic Tools for Agent Development
  3. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
  4. 2026C-World: A Computer Use Agent Environment Creator
  5. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems
  6. 2026The World Won't Stay Still: Programmable Evolution for Agent Benchmarks
  7. 2025Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
  8. 2025Control Plane as a Tool: A Scalable Design Pattern for Agentic AI Systems