MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

• URL: http://arxiv.org/abs/2605.14212v1
• Date: Thu, 14 May 2026 00:11:27 GMT
• Title: MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
• Abstract summary: We introduce MetaAgent-X, an end-to-end reinforcement learning framework that jointly optimize automatic MAS design and execution.<n>We show that MetaAgent-X consistently outperforms existing automatic MAS baselines, achieving up to 21.7% gains.<n>These results establish end-to-end trainable automatic MAS as a practical paradigm for building self-designing and self-executing agentic models.
• Score: 26.35314976395182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free test-time search or optimize the meta-level designer while keeping downstream execution agents frozen, which creating a frozen-executor ceiling and leaving the end-to-end training of self-designing and self-executing agentic models unexplored. To address this, we introduce MetaAgent-X, an end-to-end reinforcement learning framework that jointly optimizes automatic MAS design and execution. MetaAgent-X enables script-based MAS generation, execution rollout collection, and credit assignment for both designer and executor trajectories. To support stable and scalable optimization, we propose Executor Designer Hierarchical Rollout and Stagewise Co-evolution to improve training stability and expose the dynamics of designer-executor co-evolution. MetaAgent-X consistently outperforms existing automatic MAS baselines, achieving up to 21.7% gains. Comprehensive ablations show that both designer and executor improve throughout training, and that effective automatic MAS learning follows a stagewise co-evolution process. These results establish end-to-end trainable automatic MAS as a practical paradigm for building self-designing and self-executing agentic models.

Related papers

• AgentFactory: Towards Automated Agentic System Design and Optimization [19.84664549514199]
  AgentFactory is a framework that jointly optimize both foundation models and workflow structures in agentic systems.<n>We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance.<n>Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches.
  arXiv  Detail & Related papers  (2026-09-01T10:45:11Z)
• AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration [49.050688065974605]
  Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models.<n>We propose AutoMIA, an agentic framework that reformulates membership inference as an automated process of self-exploration and strategy evolution.
  arXiv  Detail & Related papers  (2026-04-01T15:17:45Z)
• Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents [18.707716142982992]
  We propose a self-evolving system to autonomously generate, train, and deploy complex model changes.<n>Our agents act as specialized Machine Learning Engineers (MLEs)<n>The effectiveness of this approach is demonstrated through several successful production launches at YouTube.
  arXiv  Detail & Related papers  (2026-02-10T19:16:52Z)
• ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Intrinsic Adaptation [60.25542764389203]
  Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks.<n>Existing approaches, relying on manual orchestration or runtime-based patches, often struggle with poor generalization and fragmented optimization.<n>We propose ToolSelf, a novel paradigm enabling tool-driven self-readjustment.
  arXiv  Detail & Related papers  (2026-02-08T09:27:18Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization [37.17893162265247]
  Youtu-Agent is a framework designed for the automated generation and continuous evolution of Large Language Model (LLM) agents.<n>Youtu-Agent features a structured configuration system that decouples execution environments, toolkits, and context management.<n> Experiments demonstrate that Youtu-Agent achieves state-of-the-art performance on WebWalkerQA (71.47%) and GAIA (72.8%) using open-weight models.
  arXiv  Detail & Related papers  (2025-12-31T04:17:36Z)
• $Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation [5.325886106098561]
  Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort.<n>This paper introduces Agent$2$, an LLM-driven agent-generates-agent framework for fully automated RL agent design.<n>Agent$2$ translates natural language task descriptions and environment code into executable RL solutions without human intervention.
  arXiv  Detail & Related papers  (2025-09-16T02:14:39Z)
• MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision [76.42361936804313]
  We introduce MAS-ZERO, the first self-evolved, inference-time framework for automatic MAS design.<n> MAS-ZERO employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance.
  arXiv  Detail & Related papers  (2025-05-21T00:56:09Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• ProAgent: From Robotic Process Automation to Agentic Process Automation [87.0555252338361]
  Large Language Models (LLMs) have emerged human-like intelligence. This paper introduces Agentic Process Automation (APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation. We then instantiate ProAgent, an agent designed to craft from human instructions and make intricate decisions by coordinating specialized agents.
  arXiv  Detail & Related papers  (2023-11-02T14:32:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.