MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

arXiv:2606.06473 · cs.AI, cs.CL · Submitted 2026-06-04 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-06-04

Updated: 2026-10-22

Comments: 24 pages, 8 figures, 6 tables. Project page: https://internscience.github.io/MLEvolve/

Code: https://github.com/InternScience/MLEvolve

Project page: https://internscience.github.io/MLEvolve

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Cross-Domain Generalization — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes

Sources

• InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
• InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
• AIDE: AI-Driven Exploration in the Space of Code
• R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
• ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
• The FM Agent
• AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
• AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
• MARS: Modular Agent with Reflective Search for Automated AI Research
• Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
• AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
• Mathematical exploration and discovery at scale
• MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
• MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
• AIBuildAI: An AI Agent for Automatically Building AI Models
• KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
• Monte-Carlo Graph Search for AlphaZero
• Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems