mlsanityData to 7 Oct 2026

AIDE: AI-Driven Exploration in the Space of Code

arXiv 2502.13138 ↗First posted 18 Feb 2025cs.AI cs.LGcited by 206

Not on the map. Why?

Cited by 118 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.

Key facts. Cited by 206 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

20 of 32 references.

References · 20

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  9. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  10. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  11. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  12. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
8 more
  1. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  2. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
  3. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 339
  4. 2020On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practicecited by 181
  5. 2020Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learningcited by 174
  6. 2018Auto-Keras: An Efficient Neural Architecture Search Systemcited by 169
  7. 2024RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human expertscited by 153
  8. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 62; 2026: 144.

206 papers.

Sort:

By area:

  1. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 375
  2. 2026Towards End-to-End Automation of AI Researchcited by 150
  3. 2025Measuring AI Ability to Complete Long Software Taskscited by 142
  4. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 86
  5. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  6. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchcited by 65
  7. 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinementcited by 52
  8. 2026Code as Agent Harnesscited by 40
  9. 2025MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineeringcited by 38
  10. 2025CodePDE: An Inference Framework for LLM-driven PDE Solver Generationcited by 37
  11. 2025R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Sciencecited by 33
  12. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 32
38 more
  1. 2026AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agentscited by 32
  2. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Researchcited by 29
  3. 2025CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimizationcited by 28
  4. 2025MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?cited by 27
  5. 2025ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineeringcited by 26
  6. 2026SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agentscited by 25
  7. 2026AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaborationcited by 23
  8. 2025MLZero: A Multi-Agent System for End-to-end Machine Learning Automationcited by 22
  9. 2026MARS: Modular Agent with Reflective Search for Automated AI Researchcited by 22
  10. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  11. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Sciencecited by 20
  12. 2025The FM Agentcited by 20
  13. 2026MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discoverycited by 20
  14. 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solvingcited by 19
  15. 2026Towards Execution-Grounded Automated AI Researchcited by 19
  16. 2025AutoMLGen: Navigating Fine-Grained Optimization for Coding Agentscited by 17
  17. 2025How Far Are AI Scientists from Changing the World?cited by 15
  18. 2026ResearchGym: Evaluating Language Model Agents on Real-World AI Researchcited by 15
  19. 2026Toward Autonomous Long-Horizon Engineering for ML Researchcited by 15
  20. 2025TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agentscited by 14
  21. 2026DSGym: A Holistic Framework for Evaluating and Training Data Science Agentscited by 14
  22. 2025PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priorscited by 13
  23. 2025Reinforcement Learning for Machine Learning Engineering Agentscited by 13
  24. 2025AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learningcited by 13
  25. 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvementscited by 12
  26. 2025WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learningcited by 11
  27. 2026Synthetic Sandbox for Training Machine Learning Engineering Agentscited by 11
  28. 2025Bootstrapping Task Spaces for Self-Improvementcited by 10
  29. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  30. 2026AIRA_2: Overcoming Bottlenecks in AI Research Agentscited by 10
  31. 2026AIBuildAI: An AI Agent for Automatically Building AI Modelscited by 10
  32. 2026Toward Generalist Autonomous Research via Hypothesis-Tree Refinementcited by 10
  33. 2026AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvementcited by 10
  34. 2025Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verificationcited by 9
  35. 2025DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automationcited by 8
  36. 2025An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Designcited by 8
  37. 2025SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Sciencecited by 7
  38. 2025AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Sciencecited by 7

50 most cited of 206 All 206 (JSON)