# AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

arXiv: https://arxiv.org/abs/2507.02554 · HTML: https://mlsanity.com/paper/2507.02554/

## Key facts

- Cited by 71 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 31 of its 56 references that are in the map.
- First posted on arXiv 3 Jul 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 31)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning](https://mlsanity.com/paper/2007.04074/) (2020)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs](https://mlsanity.com/paper/2402.15627/) (2024)
- [OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code](https://mlsanity.com/paper/2405.15568/) (2024)
- [SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge](https://mlsanity.com/paper/2308.12682/) (2023)
- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [Simple And Efficient Architecture Search for Convolutional Neural Networks](https://mlsanity.com/paper/1711.04528/) (2017)
- [Revisiting Reliability in Large-Scale Machine Learning Research Clusters](https://mlsanity.com/paper/2410.21680/) (2024)

## Built on by (most cited first, 30 of 71)

- [Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead](https://mlsanity.com/paper/2510.01624/) (2025)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://mlsanity.com/paper/2510.06186/) (2025)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents](https://mlsanity.com/paper/2510.08511/) (2025)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [AIBuildAI: An AI Agent for Automatically Building AI Models](https://mlsanity.com/paper/2604.14455/) (2026)
- [AIRA_2: Overcoming Bottlenecks in AI Research Agents](https://mlsanity.com/paper/2603.26499/) (2026)
- [KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization](https://mlsanity.com/paper/2601.21526/) (2026)
- [Synthetic Sandbox for Training Machine Learning Engineering Agents](https://mlsanity.com/paper/2604.04872/) (2026)
- [Recursive self-improvement of AI research agents](https://mlsanity.com/paper/2609.26457/) (2026)
- [Bootstrapping Task Spaces for Self-Improvement](https://mlsanity.com/paper/2509.04575/) (2025)
- [Can We Predict Before Executing Machine Learning Agents?](https://mlsanity.com/paper/2601.05930/) (2026)
- [Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries](https://mlsanity.com/paper/2606.10402/) (2026)
- [AI Research Preference Models](https://mlsanity.com/paper/2608.13940/) (2026)
- [Simple Baselines are Competitive with Code Evolution](https://mlsanity.com/paper/2602.16805/) (2026)
- [Training AI Scientists to Replicate Research](https://mlsanity.com/paper/2608.13331/) (2026)
- [Understanding the Challenges in Iterative Generative Optimization with LLMs](https://mlsanity.com/paper/2603.23994/) (2026)
- [FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics](https://mlsanity.com/paper/2605.17373/) (2026)
- [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026)
- [End-to-end PDDL Planning with Hardcoded and Dynamic Agents](https://mlsanity.com/paper/2512.09629/) (2025)
- [KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta](https://mlsanity.com/paper/2512.23236/) (2025)
- [Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design](https://mlsanity.com/paper/2605.15871/) (2026)
- [AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering](https://mlsanity.com/paper/2602.07906/) (2026)
- [Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search](https://mlsanity.com/paper/2603.01692/) (2026)
- [GEAR: Genetic AutoResearch for Agentic Code Evolution](https://mlsanity.com/paper/2605.13874/) (2026)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement](https://mlsanity.com/paper/2508.12555/) (2025)
- [ML-Tool-Bench: Tool-Augmented Planning for ML Tasks](https://mlsanity.com/paper/2512.00672/) (2025)

## Abstract (arXiv)

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39.6% to 47.7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.