# ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering

arXiv: https://arxiv.org/abs/2505.23723 · HTML: https://mlsanity.com/paper/2505.23723/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning](https://mlsanity.com/paper/2007.04074/) (2020)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [Self-Evolving Multi-Agent Collaboration Networks for Software Development](https://mlsanity.com/paper/2410.16946/) (2024)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions](https://mlsanity.com/paper/2410.20424/) (2024)
- [MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks](https://mlsanity.com/paper/2304.14979/) (2023)
- [Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation](https://mlsanity.com/paper/2402.05699/) (2024)
- [AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models](https://mlsanity.com/paper/2404.16233/) (2024)

## Built on by (most cited first, 26 of 26)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Memp: Exploring Agent Procedural Memory](https://mlsanity.com/paper/2508.06433/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [AutoMind: Adaptive Knowledgeable Agent for Automated Data Science](https://mlsanity.com/paper/2506.10974/) (2025)
- [Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2509.03817/) (2025)
- [Synthetic Sandbox for Training Machine Learning Engineering Agents](https://mlsanity.com/paper/2604.04872/) (2026)
- [Can We Predict Before Executing Machine Learning Agents?](https://mlsanity.com/paper/2601.05930/) (2026)
- [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026)
- [Learning to Ideate for Machine Learning Engineering Agents](https://mlsanity.com/paper/2601.17596/) (2026)
- [Hybrid-Gym: Training Coding Agents to Generalize Across Tasks](https://mlsanity.com/paper/2602.16819/) (2026)
- [Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization](https://mlsanity.com/paper/2509.09321/) (2025)
- [AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization](https://mlsanity.com/paper/2604.26969/) (2026)
- [AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering](https://mlsanity.com/paper/2602.07906/) (2026)
- [Scaling Automatic Research Agents via World Models](https://mlsanity.com/paper/2608.12564/) (2026)
- [ASAP: an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training](https://mlsanity.com/paper/2511.03844/) (2025)
- [Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical Analysis](https://mlsanity.com/paper/2512.00214/) (2025)
- [DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning](https://mlsanity.com/paper/2602.11089/) (2026)
- [Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills](https://mlsanity.com/paper/2609.02749/) (2026)
- [MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning](https://mlsanity.com/paper/2510.06270/) (2025)
- [1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?](https://mlsanity.com/paper/2605.17046/) (2026)
- [AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research](https://mlsanity.com/paper/2608.11216/) (2026)
- [MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development](https://mlsanity.com/paper/2609.36679/) (2026)
- [A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines](https://mlsanity.com/paper/2602.22442/) (2026)
- [Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language Model](https://mlsanity.com/paper/2606.05250/) (2026)
- [EvoRank: LLM-Guided Evolution of Multi-Objective Learning-to-Rank Pipelines](https://mlsanity.com/paper/2609.22196/) (2026)

## Abstract (arXiv)

The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the capacity to learn from execution trajectories for generalization, while large proprietary models incur high computational overhead, restricting accessibility and scalability. Focusing on this, for the first time, we explore the paradigm of learning-based agentic ML, where an LLM agent learns through interactive experimentation on ML tasks using online reinforcement learning (RL). To realize this, we propose a novel agentic ML training framework with three key components: (1) exploration-enriched fine-tuning, which enables LLM agents to generate diverse actions for enhanced RL exploration; (2) step-wise RL, which enables training on a single action step, accelerating experience collection and improving training efficiency; (3) an agentic ML-specific reward module, which unifies varied ML feedback signals into consistent rewards for RL optimization. Leveraging this framework, we train ML-Agent, driven by a 7B-sized Qwen-2.5 LLM for autonomous ML. Despite training on only 9 ML tasks, our 7B-sized ML-Agent achieves comparable performance to agents using much larger proprietary LLMs (e.g., GPT-5) but at significantly lower computational cost, demonstrating strong performance and cross-task generalization.