Recursive self-improvement of AI research agents

arXiv:2609.26457 · cs.AI, cs.LG, cs.SE · Submitted 2026-09-22 · Read on arXiv

cs.AI, cs.LG, cs.SE

Submitted: 2026-09-22

Updated: 2026-09-22

Comments: 28 pages, 10 figures, 3 tables

Code: https://github.com/algorithmicsuperintelligence/openevolve

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

Terminology

• Benchmark — 63× in this paper · explained in 2 episodes
• Reward Hacking — 17× in this paper · explained in 8 episodes
• Generalization — 9× in this paper · explained in 13 episodes
• Core — 6× in this paper · explained in 2 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Meta-learning — 5× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Continual Learning — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Self-consistency — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agentic Search — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
• Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Training AI Scientists to Replicate Research
• AI Research Preference Models
• Generalized Inner Loop Meta-Learning
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• AIRA_2: Overcoming Bottlenecks in AI Research Agents
• Open-Endedness is Essential for Artificial Superhuman Intelligence
• The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
• AIDE: AI-Driven Exploration in the Space of Code
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• WHALE: A Simple Recipe for Joint Harness-Weight Optimization
• Autodata: An agentic data scientist to create high quality synthetic data
• Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Evolution through Large Models
• Position: Agentic Evolution is the Path to Evolving LLMs
• SPADE: Self-Play in Adaptive Synthetic Executable Environments

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