$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation

• URL: http://arxiv.org/abs/2509.13368v2
• Date: Tue, 30 Sep 2025 05:06:12 GMT
• Title: $Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation
• Authors: Yuan Wei, Xiaohan Shan, Ran Miao, Jianmin Li,
• Abstract summary: 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.
• Score: 5.325886106098561
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven agent-generates-agent framework for fully automated RL agent design. Agent$^2$ autonomously translates natural language task descriptions and environment code into executable RL solutions without human intervention. The framework adopts a dual-agent architecture: a Generator Agent that analyzes tasks and designs agents, and a Target Agent that is automatically generated and executed. To better support automation, RL development is decomposed into two stages, MDP modeling and algorithmic optimization, facilitating targeted and effective agent generation. Built on the Model Context Protocol, Agent$^2$ provides a unified framework for standardized agent creation across diverse environments and algorithms, incorporating adaptive training management and intelligent feedback analysis for continuous refinement. Extensive experiments on benchmarks including MuJoCo, MetaDrive, MPE, and SMAC show that Agent$^2$ outperforms manually designed baselines across all tasks, achieving up to 55\% performance improvement with consistent average gains. By enabling a closed-loop, end-to-end automation pipeline, this work advances a new paradigm in which agents can design and optimize other agents, underscoring the potential of agent-generates-agent systems for automated AI development.

Related papers

• AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent [57.10083973844841]
  AgentArk is a novel framework to distill multi-agent dynamics into the weights of a single model.<n>We investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios.<n>By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents.
  arXiv  Detail & Related papers  (2026-02-03T19:18:28Z)
• 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)
• Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
  Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T05:01:57Z)
• InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios [28.65914611521654]
  InfiAgent is a Pyramid-like DAG-based Multi-Agent Framework that can be applied to textbfinfinite scenarios.<n>InfiAgent achieves 9.9% higher performance compared to ADAS (similar auto-generated agent framework)
  arXiv  Detail & Related papers  (2025-09-26T15:44:09Z)
• AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications [95.42093979627703]
  AgentScope supports flexible and efficient tool-based agent-environment interactions.<n>We ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure.<n>AgentScope also includes robust engineering support for developer-friendly experiences.
  arXiv  Detail & Related papers  (2025-08-22T10:35:56Z)
• Agent Lightning: Train ANY AI Agents with Reinforcement Learning [24.13422767414729]
  We present Agent Lightning, a framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent.<n>By formulating agent execution as Markov decision process, we define an unified data interface and propose a hierarchical RL algorithm, LightningRL, which contains a credit assignment module.<n>For the system design, we introduce a Training-Agent Disaggregation architecture, and brings agent observability frameworks into agent runtime.
  arXiv  Detail & Related papers  (2025-08-05T17:50:13Z)
• AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents [4.57755315319748]
  Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making.<n>These frameworks predominantly serve developers with extensive technical expertise.<n>Only 0.03 % of the global population possesses the necessary programming skills.
  arXiv  Detail & Related papers  (2025-02-09T16:53:56Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• 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)
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning [56.887047551101574]
  We present DS-Agent, a novel framework that harnesses large language models (LLMs) agent and case-based reasoning (CBR) In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle. In the deployment stage, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm, significantly reducing the demand on foundational capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-02-27T12:26:07Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)

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.