Open-Endedness

Open-Endedness Quality Diversity

Evolve diverse populations of challenges and agents without an archive or pre-defined behavioral dimensions.

MAP-Elites

Open-Endedness AI4Science

How LLM agents can be used to pursue mathematical research at scale, by Terence Tao et al.

AlphaEvolve

Open-Endedness Reinforcement Learning Quality Diversity Exploration

Go-Explore

How to explore RL search space better than intrinsic motivation.

MAP-Elites PPO - Proximal Policy Optimization Monte-Carlo Tree Search

Open-Endedness LLM Agents

Learn agentic architecture without manual design.

Darwin Godel Machine (DGM)

Open-Endedness Quality Diversity Self Play

Learn policy in open-ended loop with self-play and LLMs.

Darwin Godel Machine (DGM) MAP-Elites

Open-Endedness LLM Agents

How can agents improve themselves? Self-modify and validate if it works + maintain library of previous agents as stepping stones.

AlphaEvolve MAP-Elites Go-Explore

Open-Endedness Large Language Models (LLMs)

How to measure notions of interestingness without hand-coded formulas for learning agents

PPO - Proximal Policy Optimization

Open-Endedness AI4Science LLM Agents

How to use LLM agents to drive scientific workflow

Open-Endedness Quality Diversity

MAP-Elites

Create and maintain rich diversity of high performing solutions, often outperforming direct performance optimization.

Go-Explore AlphaEvolve Gaussian Processes Challenges of optimizing deep models Stochastic Gradient Descent