Synthetic ecosystems, emergent creatures, evolution. What is life really? Free paper at: "Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata," arxiv.org/abs/2506.08569 Video used by permission of Erwan Plantec, erwan plantec.

Extended Flow-#Lenia paper is out in Artificial Life journal , with more experiments and insights! See 🧵 from 1st-author erwan plantec below for a summary. For a full overview of Inria Flowers team research in Artificial Life, here is a talk I gave at Demeco : youtube.com/watch?v=YYFrWN…

Inference-Time Scaling and Collective Intelligence for Frontier AI sakana.ai/ab-mcts/ We developed AB-MCTS, a new inference-time scaling algorithm that enables multiple frontier AI models to cooperate, achieving promising initial results on the ARC-AGI-2 benchmark.

Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!) It brings LLMs from just a few percent on ARC-AGI-1 up to 52% We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code. 🧵

Introducing Concordia 2.0, an update to our library for building multi-actor LLM simulations!! 🚀 We view multi-actor generative AI as a game engine. The new version is built on a flexible Entity-Component architecture, inspired by modern game development.

🦎 Thank you all for a great first edition of the workshop "Evolving self-organisation" yesterday at GECCO 2025 It's been a great mix of artificial life and GECCO vibes. Especially thanks to our organisers Alex Mordvintsev Sebastian Risi Eyvind Niklasson Ettore Randazzo Milton Joachim Winther Pedersen

"When does Neuro-evolution out-compete Reinforcement Learning in Transfer Learning tasks?" Find us at GECCO 2025 where we are presenting this work of our Grow-AI team with Sebastian Risi Milton Joachim Winther Pedersen erwan plantec arxiv.org/abs/2505.22696 sebastianrisi.com/grow-ai/

RL is back! But is it always the best choice? In a new paper, we investigate under what circumstances neuroevolution outperforms RL in transfer learning tasks. See more details in the thread below 🧵 While NE performs best in simpler domains, it will be interesting to see if the