open-endedness

Accelerated Quality-Diversity

Cellular Automata Accelerated in JAX (Oral at ICLR 2025)

Group Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).

Word2World is an LLM-based PCG system that creates playable 2D world from stories

Repository for "Toward Artificial Open-Ended Evolution within Lenia using Quality-Diversity" (ALIFE 2024).

Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization

Implementation and explorations into PopuLoRA, Co-Evolving LLM Populations for Reasoning Self-Play

Open-ended natural selection of interacting code-data-dual algorithms as a property analogous to Turing completeness.

🤖 The most comprehensive, community-driven resourcefor Automated AI Research — papers, tools, people, lbs, roadmaps. Featuring Recursive Lab, Sakana AI, DepMind & beyond.

CodonTrace Genesis — deterministic research software for digital evolution, causal mechanism auditing, replayable ALife experiments, and evidence-gated AI/evolution studies.

Code for our paper HeXA: Hierarchical Experimentalist Agents

DISCOvery engine: the agent invents its own questions, predicts before it runs, keeps only machine-verified, reality-culled claims — self-evolving methodology, multi-agent science. Procedurally-generated contamination-free worlds make discovery an RL environment: execution-anchored rewards, SFT/GRPO-ready trajectories.

Distilling SotA open-endedness through open-endedness: a self-updating knowledge base, trend tracker, and research-idea generator

Code Mode MCP server for Websets. Supports two-stage validation/exploratory research.

ATEP is an open-ended learning system that introduces species-based evolution of Enhanced-POET.

Repository for "Toward Artificial Open-Ended Evolution within Lenia using Quality-Diversity" (ALIFE 2024) webpage.

Promotion gate and verifier toolbox for AI systems: exposure audits, paired PASS/HOLD/BLOCK receipts, disposable public report cards, and an open MCP endpoint.

Code for the assemblyca publication in NeurIPS ALOE workshop

A research monograph on ASI alignment beyond external control, developing immanent teleology, developmental basins, process-bound identity, reciprocal constitutional governance, shared viable possibility space, and heterogeneous intelligence ecologies.