mlsanityData to 7 Oct 2026

Dataforge: Agentic Platform for Autonomous Data Engineering

arXiv 2511.06185 ↗First posted 9 Nov 2025cs.AIcited by 1

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

The growing demand for artificial intelligence (AI) applications in materials discovery, molecular modeling, and climate science has made data preparation a critical but labor-intensive bottleneck. Raw data from diverse sources must be cleaned, normalized, and transformed to become AI-ready, where effective feature transformation and selection are essential for robust learning. We present Dataforge, an LLM-powered agentic data engineering platform for tabular data that is automatic, safe, and non-expert friendly. It autonomously performs data cleaning and iteratively optimizes feature operations under a budgeted feedback loop with automatic stopping. Across tabular benchmarks, it achieves the best overall downstream performance; ablations further confirm the roles of routing/iterative refinement and grounding in accuracy and reliability. Dataforge demonstrates a practical path toward autonomous data agents that transform raw data from data to better data.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 29 of its 65 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

29 of 65 references.

References · 29

  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  2. 2023Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineeringcited by 125
  3. 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 79
  4. 2017Feature Engineering for Predictive Modeling using Reinforcement Learningcited by 78
  5. 2019The autofeat Python Library for Automated Feature Engineering and Selectioncited by 73
  6. 2024MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learningcited by 66
  7. 2022OpenFE: Automated Feature Generation with Expert-level Performancecited by 52
  8. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  9. 2023Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossingcited by 30
  10. 2024Evolutionary Large Language Model for Automated Feature Transformationcited by 29
  11. 2023Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selectioncited by 28
  12. 2022Traceable Automatic Feature Transformation via Cascading Actor-Critic Agentscited by 26
17 more
  1. 2023Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspectivecited by 24
  2. 2023Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressionscited by 23
  3. 2024Feature Selection as Deep Sequential Generative Learningcited by 21
  4. 2024Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuningcited by 21
  5. 2021Efficient Reinforced Feature Selection via Early Stopping Traverse Strategycited by 19
  6. 2020Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loopcited by 18
  7. 2020Simplifying Reinforced Feature Selection via Restructured Choice Strategy of Single Agentcited by 14
  8. 2024Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agentcited by 14
  9. 2025A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspectivecited by 14
  10. 2025Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformationcited by 13
  11. 2024Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Explorationcited by 11
  12. 2024Topology-aware Reinforcement Feature Space Reconstruction for Graph Datacited by 11
  13. 2025Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teamingcited by 11
  14. 2025Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memoriescited by 9
  15. 2025Autonomous Data Agents: A New Opportunity for Smart Datacited by 6
  16. 2025LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformationcited by 5
  17. 2025Distribution Shift Aware Neural Tabular Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
  2. 2026Exploring Autonomous Agentic Data Engineering for Model Specialization
  3. 2026Evaluating a 4B open-weights local LLM for agentic DFT workflows: a literature reproducibility audit
  4. 2026Agentic programs: an emerging form of scientific software in computational materials science
  5. 2026Towards Agentic Intelligence for Materials Science
  6. 2026AgenticDataBench: A Comprehensive Benchmark for Data Agents
  7. 2025DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
  8. 2026From Data to Theory: Autonomous Large Language Model Agents for Materials Science