Learning the ARTS of Search for Automated Discovery

arXiv:2606.21891 · cs.AI, cs.CL · Submitted 2026-06-20 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-06-20

Updated: 2026-08-26

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

Project page: https://auto-discovery.github.io/arts

Terminology

• Ablation — 18× in this paper · explained in 1 episode
• GRPO — 10× in this paper · explained in 6 episodes
• Regularization — 9× in this paper · explained in 3 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Agentic Reasoning — 6× in this paper · explained in 1 episode
• Agentic Reasoning for Tree Search — 5× in this paper
• Trace — 5× in this paper · explained in 2 episodes
• AUC — 4× in this paper · explained in 2 episodes
• Actor — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• LoRA Adapters — 3× in this paper · explained in 3 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Action Masking — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Credit assignment — 2× in this paper · explained in 3 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feature Engineering — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Random Network Distillation — 1× in this paper
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Understanding LoRA as Knowledge Memory: An Empirical Analysis
• OpenAI Gym
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
• MARS: Modular Agent with Reflective Search for Automated AI Research
• SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
• ARC Prize 2024: Technical Report
• FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
• Accelerating scientific discovery with Co-Scientist
• LLM-First Search: Self-Guided Exploration of the Solution Space
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• AIDE: AI-Driven Exploration in the Space of Code
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Towards Execution-Grounded Automated AI Research
• Learning to (Learn at Test Time): RNNs with Expressive Hidden States
• Amplifying human performance in combinatorial competitive programming
• Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection