mlsanityData to 7 Oct 2026

R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science

arXiv 2505.14738 ↗First posted 20 May 2025cs.AIcited by 33

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Recent advances in AI and ML have transformed data science, yet increasing complexity and expertise requirements continue to hinder progress. Although crowd-sourcing platforms alleviate some challenges, high-level machine learning engineering (MLE) tasks remain labor-intensive and iterative. We introduce R&D-Agent, a comprehensive, decoupled, and extensible framework that formalizes the MLE process. R&D-Agent defines the MLE workflow into two phases and six components, turning agent design for MLE from ad-hoc craftsmanship into a principled, testable process. Although several existing agents report promising gains on their chosen components, they can mostly be summarized as a partial optimization from our framework's simple baseline. Inspired by human experts, we designed efficient and effective agents within this framework that achieve state-of-the-art performance. Evaluated on MLE-Bench, the agent built on R&D-Agent ranks as the top-performing machine learning engineering agent, achieving 35.1% any medal rate, demonstrating the ability of the framework to speed up innovation and improve accuracy across a wide range of data science applications. We have open-sourced R&D-Agent on GitHub: https://github.com/microsoft/RD-Agent.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 27 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

15 of 27 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering9 Oct
  2. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?12 Sep
  3. 2024InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation8 Jul
  4. 2024DiscoveryBench: Towards Data-Driven Discovery with Large Language Models1 Jul
  5. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation5 Oct

Other references · 10

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  3. 2020AutoGluon-Tabular: Robust and Accurate AutoML for Structured Datacited by 368
  4. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 206
  5. 2021Scaling Laws for Neural Machine Translationcited by 110
  6. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  7. 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Marketscited by 46
  8. 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 29
  9. 2024MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelscited by 22
  10. 2024ContextGNN: Beyond Two-Tower Recommendation Systemscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 30.

33 papers.

Sort:

By area:

  1. 2025ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoningcited by 57
  2. 2026MARS: Modular Agent with Reflective Search for Automated AI Researchcited by 22
  3. 2026MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discoverycited by 20
  4. 2026Toward Autonomous Long-Horizon Engineering for ML Researchcited by 15
  5. 2026Synthetic Sandbox for Training Machine Learning Engineering Agentscited by 11
  6. 2026Can We Predict Before Executing Machine Learning Agents?cited by 10
  7. 2026KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimizationcited by 10
  8. 2026AIBuildAI: An AI Agent for Automatically Building AI Modelscited by 10
  9. 2026AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systemscited by 8
  10. 2026Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineeringcited by 7
  11. 2025DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queriescited by 6
  12. 2026EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scalecited by 4
21 more
  1. 2026LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysiscited by 4
  2. 2025ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challengescited by 3
  3. 2026What Do Evolutionary Coding Agents Evolve?cited by 3
  4. 2026ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyondcited by 3
  5. 2026Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Noveltycited by 2
  6. 2026SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithmscited by 1
  7. 2026AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Modelscited by 1
  8. 2026Towards Autonomous and Auditable Medical Imaging Model Developmentcited by 1
  9. 2026Recovering Wasted Compute in Autoresearch Agentscited by 1
  10. 2026What is Missing from AI Post-Training AI: An Empirical Analysiscited by 1
  11. 2026OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spacescited by 0
  12. 2026VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observerscited by 0
  13. 2026Evolving Executable Pipeline Programs for AutoML with Language Modelscited by 0
  14. 2026TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Developmentcited by 0
  15. 2026DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automationcited by 0
  16. 2026PrimeScientist: Strategic Allocation of Research Effort in Autonomous Researchcited by 0
  17. 2026Token Signatures of Code: Comparing Coding Behaviors Across Large Language Modelscited by 0
  18. 2026Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuningcited by 0
  19. 2026AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Searchcited by 0
  20. 2026TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Modelscited by 0
  21. 2026How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
  2. 2025CoMind: Towards Community-Driven Agents for Machine Learning Engineering
  3. 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
  4. 2025ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
  5. 2026DeltaML-Bench: Evaluating Machine Learning Agents on Real-World Research Repositories
  6. 2025ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
  7. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
  8. 2026ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments