🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

What can LLMs bring to the study of cultural evolution? 🤔 In this preprint, we present a framework for simulating cultural evolution using LLMs 🦜 We study how the dynamics depends on social structure, simulated personalities👥, and whether it has potential attractors🧲🔍 1/17

1/⚡️Looking for a fast and simple Transformer baseline for your RL environment in JAX ? Sharing my implementation of transformerXL-PPO: github.com/Reytuag/transf… The implementation is the first to attain the 3rd floor and obtain advanced achievements in the challenging Craftax

What happens when LLMs play the Telephone game? ☎️ In this new preprint, we analyse the evolution of texts as they are transmitted between LLM agents 🤖💬🤖💬🤖💬 Do text properties converge to attractors? 🧲 How is this influenced by the task📝 and model⚙️? 1/13🧵

🚨 NEW LEADERBOARD ! 🚨 We instruct LLMs to role-play and then add a long context. Which LLMs best Stick to Their Role? Imagine asking several LLMs to play a role, then discuss various topics. Which ones best stick to their role? 🥇 Mistral-Large 🥈 Qwen2.5-72B 🥉 Llama3.1_70b 🧵

Excited to share with @flowersINRIA ADTool, an open-source Python toolkit using curiosity-driven AI to explore behavior diversity of complex systems (cellular automata, physics models, ...)!🐍 Serving off-the-shelf strategies like IMGEP github.com/flowersteam/ad… You said IMGEP? 👇

🚀 Introducing 🧭MAGELLAN—our new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.🌍✨Learn more: 🔗 arxiv.org/abs/2502.07709 #OpenEndedLearning #LLM #RL

🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥 In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with Stefano Palminteri (@stepalminteri.bsky.social) and Pierre-Yves Oudeyer ! Here is a brief recap ⬇️

Check out this work today at 10 am ICLR 2026! Learn what's wrong with evaluating #LLMs after a single interaction, and how cultural attraction theory can help us do better. Poster #288 Jérémy Perez Pierre-Yves Oudeyer Maxime Derex Grgur Kovač Cédric Corentin LEGER Clément Moulin-Frier

Generative AI is a cultural transmission technology: it plays a growing role in generation, selection and transmission of ideas/opinions in human society 🧠🔄🌐 And yet we understand very little of this dynamics at this point 🤔❓ A step forward is our #ICLR2025 paper !👇

I'm happy to share that MAGELLAN has been accepted at #ICML2025! 🎉 See you in Vancouver!

I'll be at RLDM this week to present our new paper: WorldLLM 😃 In the same spirit as our previous works — e.g. GLAM, MAGELLAN... — which investigate how to ground LLMs through interactions with external environments, WorldLLM takes a deep dive into the world modeling aspect.

🔔 Join our MAGELLAN talk on July 2! We'll explore how LLM agents can monitor their own learning progress and choose what to learn next, like curious humans 🤔 1h presentation + 1h Q&A on autotelic agents & more! 📅 July 2, 4:30 PM CEST 🎟️ forms.gle/1PC2fxJx1PZYfq…

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. 🧵