Assembling Insights for Agentic Machine Learning Engineering Systems
cs.SE, cs.AI, cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/openai/mlebench
Sources
- AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
- MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
- AIDE: AI-Driven Exploration in the Space of Code
- The FM Agent
- ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
- LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
- R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
- AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
- Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties