🔥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

Large Language Models #LLMs are black boxes. In this thread, I am going to summarize a couple of (open) tools that we developed (mainly the amazing Nicolas Yax with the invaluable help of Pierre-Yves Oudeyer ) to solve some of these issues and empower robust and reproducible research

we are recruiting interns for a few projects with Pierre-Yves Oudeyer in bordeaux > studying llm-mediated cultural evolution with Eleni Nisioti Jérémy Perez > balancing exploration and exploitation with autotelic rl with Clément ROMAC details and links in 🧵 please share!

🚀 Exciting Internship Opportunities for AI and CogSci Students🌟 Join Inria Flowers team and work on these cool topics: 🔧 Curriculum learning of skill libraries in autotelic agents using LLMs and program synthesis wth Pourcel Julien 🎯 Balancing Exploration and Exploitation in

We just opened a new (engineering) internship position in the Inria Flowers team team with Pierre-Yves Oudeyer: docs.google.com/document/d/13V… We'll focus on developing our lamorel library, which has been central to our recent work on grounding embodied LLMs (more below 👇1/4)

🚀 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

Enabling forms of metacognition in LLMs is a frontiers challenge in #AI We've made progress in this direction: 🧭MAGELLAN allows curiosity-driven LLMs to learn to predict and generalize their own learning progress, and navigate in very large spaces of goals 🚀 Details here 👇

🧠 One of the key limitation of LLMs today is their lack of metacognition: they were (mostly) not trained to know what they know or don't know, what they can or can't do. 🚀At Inria Flowers team, we're proposing an approach to build metacognition into LLMs: MAGELLAN !

Curious about LLM interpretability and understanding ? We borrowed concepts from genetics to map language models, predict their capabilities, and even uncovered surprising insights about their training ! Come see my poster at #ICLR2025 3pm Hall 2B #505 !

New blog post ! What if LLM agents could learn by doing, not just by reading? 🤔 2024 was the year of "agentic AI"—systems that plan, act, and execute complex workflows autonomously. But current agents face critical limitations... 🧵