Clément ROMAC @ ICML 2025
261 posts
@ClementRomac
Research Scientist at 🤗 @huggingface, PhD. student at @FlowersINRIA. Studying how autonomous Deep RL agents 🤖 can leverage LLMs 📖 Also playing bass 🎸
🥳 🎊 🎉 Exciting News! Our paper "Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning" has been accepted for ICML2023. We have posted a new version on arxiv with 𝗶𝗺𝗽𝗿𝗼𝘃𝗲𝗱 𝗿𝗲𝘀𝘂𝗹𝘁𝘀 to celebrate 🎉📝 arxiv.org/abs/2302.02662
ARC Prize 2025 Winners Interviews Paper Award 2nd Place @PourcelJulien, @cedcolas, @pyoudeyer discuss SOAR - a self-improving evolutionary program synthesis framework that fine-tunes an LLM on its own search traces - without human-engineered DSLs or solution datasets.
After four incredible years in the Flowers AI & CogSci Lab, I’m thrilled to share that I’ve officially become a Doctor! 🎓💫 My thesis: “Language as a Cognitive Tool for Open Agents.” It explores how language helps artificial agents explore, adapt, and learn efficiently.
🚀 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
🔔 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 🧭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
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.
