# MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

arXiv: https://arxiv.org/abs/2505.13941 · HTML: https://mlsanity.com/paper/2505.13941/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 37 of its 84 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [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)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Using Large Language Models for Hyperparameter Optimization](https://mlsanity.com/paper/2312.04528/) (2023)
- [AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions](https://mlsanity.com/paper/2410.20424/) (2024)
- [Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model](https://mlsanity.com/paper/2401.17868/) (2024)
- [OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning](https://mlsanity.com/paper/2502.11271/) (2025)
- [Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models](https://mlsanity.com/paper/2308.00675/) (2023)
- [Large Language Model Agent for Hyper-Parameter Optimization](https://mlsanity.com/paper/2402.01881/) (2024)
- [Large Language Models as Data Preprocessors](https://mlsanity.com/paper/2308.16361/) (2023)
- [TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications](https://mlsanity.com/paper/2311.02971/) (2023)

## Built on by (most cited first, 24 of 24)

- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents](https://mlsanity.com/paper/2510.08511/) (2025)
- [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)
- [DataMaster: Data-Centric Autonomous AI Research](https://mlsanity.com/paper/2605.10906/) (2026)
- [Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering](https://mlsanity.com/paper/2606.30911/) (2026)
- [CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments](https://mlsanity.com/paper/2606.06399/) (2026)
- [Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering](https://mlsanity.com/paper/2607.25090/) (2026)
- [Exploit More, Explore Smarter for Budget-Constrained Agentic Search](https://mlsanity.com/paper/2608.23848/) (2026)
- [LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data](https://mlsanity.com/paper/2507.13413/) (2025)
- [Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data](https://mlsanity.com/paper/2509.21465/) (2025)
- [SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations](https://mlsanity.com/paper/2511.00685/) (2025)
- [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026)
- [AgentGA: Evolving Code Solutions in Agent-Seed Space](https://mlsanity.com/paper/2604.14655/) (2026)
- [CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution](https://mlsanity.com/paper/2605.13295/) (2026)
- [Be Fair! Can Machine Learning Engineering Agents Adhere to Fairness Constraints?](https://mlsanity.com/paper/2606.04971/) (2026)
- [iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML](https://mlsanity.com/paper/2602.13937/) (2026)
- [A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines](https://mlsanity.com/paper/2602.22442/) (2026)
- [Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models](https://mlsanity.com/paper/2609.22097/) (2026)
- [Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning](https://mlsanity.com/paper/2609.22257/) (2026)
- [Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions](https://mlsanity.com/paper/2609.38593/) (2026)
- [How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?](https://mlsanity.com/paper/2609.40303/) (2026)
- [ML Engineering Agents - A Data Management Perspective](https://mlsanity.com/paper/2610.16919/) (2026)

## Abstract (arXiv)

Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel multi-agent framework powered by Large Language Models (LLMs) that enables end-to-end ML automation across diverse data modalities with minimal human intervention. A cognitive perception module is first employed, transforming raw multimodal inputs into perceptual context that effectively guides the subsequent workflow. To address key limitations of LLMs, such as hallucinated code generation and outdated API knowledge, we enhance the iterative code generation process with semantic and episodic memory. MLZero demonstrates superior performance on MLE-Bench Lite, outperforming all competitors in both success rate and solution quality, securing six gold medals. Additionally, when evaluated on our Multimodal AutoML Agent Benchmark, which includes 25 more challenging tasks spanning diverse data modalities, MLZero outperforms the competing methods by a large margin with a success rate of 0.92 (+263.6%) and an average rank of 2.28. Our approach maintains its robust effectiveness even with a compact 8B LLM, outperforming full-size systems from existing solutions.