mlsanityData to 14 Oct 2026

ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning

arXiv 2506.16499 ↗First posted 19 Jun 2025cs.AI cs.LGcited by 61

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

As AI capabilities advance toward and potentially beyond human-level performance, a natural transition emerges where AI-driven development becomes more efficient than human-centric approaches. A promising pathway toward this transition lies in AI-for-AI (AI4AI), which leverages AI techniques to automate and optimize the design, training, and deployment of AI systems themselves. While LLM-based agents have shown the potential to realize AI4AI, they are often unable to fully leverage the experience accumulated by agents during the exploration of solutions in the reasoning process, leading to inefficiencies and suboptimal performance. To address this limitation, we propose ML-Master, a novel AI4AI agent that seamlessly integrates exploration and reasoning by employing a selectively scoped memory mechanism. This approach allows ML-Master to efficiently combine diverse insights from parallel solution trajectories with analytical reasoning, guiding further exploration without overwhelming the agent with excessive context. We evaluate ML-Master on the MLE-Bench, where it achieves a 29.3% average medal rate, significantly surpassing existing methods, particularly in medium-complexity tasks, while accomplishing this superior performance within a strict 12-hour time constraint-half the 24-hour limit used by previous baselines. These results demonstrate ML-Master's potential as a powerful tool for advancing AI4AI.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 20 of its 52 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

20 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Qwen2.5-Coder Technical Report18 Sep

Other references · 19

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 469
  4. 2020AutoGluon-Tabular: Robust and Accurate AutoML for Structured Datacited by 383
  5. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  6. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  7. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  8. 2020Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learningcited by 174
  9. 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 143
  10. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  11. 2025Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversationscited by 96
  12. 2023AutoML-GPT: Automatic Machine Learning with GPTcited by 81
7 more
  1. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 74
  2. 2024AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitionscited by 70
  3. 2023MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Taskscited by 66
  4. 2025R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Sciencecited by 41
  5. 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 30
  6. 2024SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learningcited by 24
  7. 2019Automated Machine Learning with Monte-Carlo Tree Searchcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 45.

61 papers.

Sort:

By area:

  1. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
  2. 2026Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineeringcited by 28
  3. 2026MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discoverycited by 28
  4. 2026MARS: Modular Agent with Reflective Search for Automated AI Researchcited by 25
  5. 2026ResearchGym: Evaluating Language Model Agents on Real-World AI Researchcited by 22
  6. 2026Toward Generalist Autonomous Research via Hypothesis-Tree Refinementcited by 22
  7. 2025The FM Agentcited by 21
  8. 2025AutoMLGen: Navigating Fine-Grained Optimization for Coding Agentscited by 18
  9. 2026Toward Autonomous Long-Horizon Engineering for ML Researchcited by 17
  10. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  11. 2026AIBuildAI: An AI Agent for Automatically Building AI Modelscited by 13
  12. 2026AIRA_2: Overcoming Bottlenecks in AI Research Agentscited by 12
38 more
  1. 2026Synthetic Sandbox for Training Machine Learning Engineering Agentscited by 11
  2. 2025Bootstrapping Task Spaces for Self-Improvementcited by 10
  3. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  4. 2025KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problemscited by 8
  5. 2025Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scalecited by 8
  6. 2026InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problemcited by 8
  7. 2026TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Explorationcited by 8
  8. 2026Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineeringcited by 8
  9. 2026Learning to Ideate for Machine Learning Engineering Agentscited by 7
  10. 2026EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scalecited by 7
  11. 2025CoMind: Towards Community-Driven Agents for Machine Learning Engineeringcited by 5
  12. 2025Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimizationcited by 5
  13. 2026ASI-Evolve: AI Accelerates AIcited by 5
  14. 2026NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelinescited by 4
  15. 2026Reasoning as Gradient: Scaling MLE Agents Beyond Tree Searchcited by 4
  16. 2026GEAR: Genetic AutoResearch for Agentic Code Evolutioncited by 4
  17. 2026ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyondcited by 4
  18. 2025Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancementcited by 3
  19. 2025MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretrainingcited by 3
  20. 2025ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challengescited by 3
  21. 2026AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Modelscited by 3
  22. 2025ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineeringcited by 2
  23. 2025PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Researchcited by 2
  24. 2026Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASHcited by 2
  25. 2026SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithmscited by 2
  26. 2026Towards Autonomous and Auditable Medical Imaging Model Developmentcited by 2
  27. 2026Recovering Wasted Compute in Autoresearch Agentscited by 2
  28. 2026Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligencecited by 2
  29. 2025MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learningcited by 1
  30. 2025SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generationcited by 1
  31. 2026SciDER: Scientific Data-centric End-to-end Researchercited by 1
  32. 2026SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoningcited by 1
  33. 2026ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent Systemcited by 1
  34. 2026Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Designcited by 1
  35. 2026Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methodscited by 1
  36. 2026Stateless Language Agents: Scaling Long-Horizon Automated Researchcited by 1
  37. 2025ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspectivecited by 0
  38. 2025Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimizationcited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
  2. 2025ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
  3. 2026Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
  4. 2025MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
  5. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
  6. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
  7. 2026Memory Intelligence Agent
  8. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond