Changelog

How the field — and our distillation of it — moves over time.

2026-06-19 · run 20260619T090215

3 added · 0 removed · 0 changed · 0 new ideas · upstream diff

Added

DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems (papers)
Dreaming in Code for Curriculum Learning in Open-Ended Worlds (papers)
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models (papers)

2026-06-18 · run 20260618T154106

97 added · 0 removed · 0 changed · 2 new ideas · upstream diff

Initial build.

Added

Exploiting Open-Endedness to Solve Problems Through the Search for Novelty (papers)
Identifying Necessary Conditions for Open-Ended Evolution through the Artificial Life World of Chromaria (papers)
Minimal Criterion Coevolution: A New Approach to Open-Ended Search (papers)
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions (papers)
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions (papers)
Co-generation of game levels and game-playing agents (papers)
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design (papers)
Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment (papers)
Prioritized Level Replay (papers)
Replay-Guided Adversarial Environment Design (papers)
Environment Generation for Zero-Shot Compositional Reinforcement Learning (papers)
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research (papers)
Open-Ended Learning Leads to Generally Capable Agents (papers)
SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning (papers)
EvoCraft: A New Challenge for Open-Endedness (papers)
Video Games as a Testbed for Open-Ended Phenomena (papers)
Open-ended search for environments and adapted agents using map-elites (papers)
Minimal Criterion Artist Collective (papers)
Evolving Curricula with Regret-Based Environment Design (papers)
Evolution through Large Models (papers)
RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments (papers)
Transfer Dynamics in Emergent Evolutionary Curricula (papers)
Watts: Infrastructure for Open-Ended Learning (papers)
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge (papers)
Grounding Aleatoric Uncertainty in Unsupervised Environment Design (papers)
Language and Culture Internalisation for Human-Like Autotelic AI (papers)
Flow-Lenia: Towards open-ended evolution in cellular automata through mass conservation and parameter localization (papers)
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning (papers)
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions (papers)
Human-Timescale Adaptation in an Open-Ended Task Space (papers)
Deep Laplacian-based Options for Temporally-Extended Exploration (papers)
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design (papers)
Voyager: An Open-Ended Embodied Agent with Large Language Models (papers)
Augmenting Autotelic Agents with Large Language Models (papers)
Reward-Free Curricula for Training Robust World Models (papers)
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (papers)
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation (papers)
Motif: Intrinsic Motivation from Artificial Intelligence Feedback (papers)
Eureka: Human-Level Reward Design via Coding Large Language Models (papers)
Practical PCG Through Large Language Models (papers)
Augmentative Topology Agents For Open-Ended Learning (papers)
OMNI: Open-endedness via Models of human Notions of Interestingness (papers)
Quality-Diversity through AI Feedback (papers)
Quality Diversity through Human Feedback (papers)
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement (papers)
Multi-Agent Diagnostics for Robustness via Illuminated Diversity (papers)
Evolutionary Optimization of Model Merging Recipes (papers)
Discovering Preference Optimization Algorithms with and for Large Language Models (papers)
Generative Design through Quality-Diversity Data Synthesis and Language Models (papers)
OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (papers)
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning (papers)
Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction (papers)
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models (papers)
Genie: Generative Interactive Environments (papers)
Debating with More Persuasive LLMs Leads to More Truthful Answers (papers)
Toward Artificial Open-Ended Evolution within Lenia using Quality-Diversity (papers)
Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents (papers)
DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft (papers)
Large Language Models as In-context AI Generators for Quality-Diversity (papers)
Word2World: Generating Stories and Worlds through Large Language Models (papers)
The AI Scientist: Towards fully automated open-ended scientific discovery (papers)
Automated design of agentic systems (papers)
Automated Capability Discovery via Model Self-Exploration (papers)
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search (papers)
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement (papers)
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective (papers)
Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis (papers)
Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models (papers)
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents (papers)
Learning to Continually Learn via Meta-learning Agentic Memory Designs (papers)
Hyperagents (papers)
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery (papers)
Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity (safety)
Managing extreme AI risks amid rapid progress (safety)
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts (safety)
Safety is Essential for Responsible Open-Ended Systems (safety)
AgenticRed: Optimizing Agentic Systems for Automated Red-teaming (safety)
Why Greatness Cannot Be Planned: The Myth of the Objective (surveys)
Open-endedness: The last grand challenge you’ve never heard of (surveys)
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (surveys)
Creative Problem Solving in Artificially Intelligent Agents: A Survey and Framework (surveys)
Executive Function: A Contrastive Value Policy for Resampling and Relabeling Perceptions via Hindsight Summarization? (surveys)
General Intelligence Requires Rethinking Exploration (surveys)
Open-Endedness is Essential for Artificial Superhuman Intelligence (surveys)
Evolution and The Knightian Blindspot of Machine Learning (surveys)
Interactive poetry breeding through Mixtral base model LLMs (blogs)
Identifying Life-Changing Books with LLMs (blogs)
SerendipityLM: Interactive evolutionary exploration of generative design spaces with large language models (blogs)
AI That Can Improve Itself (blogs)
The Future of AI is Open-Ended (blogs)
The Science of Intelligent Exploration (blogs)
Bootstrapping Intelligence: Self-Improving Systems for Open-Ended Discovery (blogs)
Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer (POET) (videos)
Novel Opportunities in Open-Endedness (videos)
Improving Deep Reinforcement Learning via Quality Diversity, Open-Ended and AI-Generating Algorithms (videos)
Open-Endedness, World Models, and the Automation of Innovation (videos)
Open-ended and AI-generating algorithms in the era of foundation models (videos)