Pierre-Yves Oudeyer
@pyoudeyer
Followers
6K
Following
3K
Media
721
Statuses
4K
Research director @inria, Head of @flowersInria lab, prev. @MSFTResearch @SonyCSLParis https://t.co/1q6Kg2FOpq https://t.co/p4lzQP6BQv
Bordeaux
Joined September 2013
🌍How to ground generative AI in the external world? 🤖How to turn LLMs into curious agents that spontaneously explore, set their own goals, and become open-ended learners? 🤝How to align such agents on the social environment? 📺In this talk, I outline a research program I
5
20
75
It seems we (@PourcelJulien @cedcolas and I) and now on some sort of funny card of the ARC-AGI prize, maybe this becomes a board game at some point, that would be cool :)
@arcprize @PourcelJulien @cedcolas @pyoudeyer Huge congrats to the team! Here’s a tribute from the fans 🙂
0
0
9
ARC Prize 2025 competition concluded today - The year of Refinements Our goal is to bring meaningful open source research into the community and today we awarded $137K to 14 teams Benchmarks matter, but their true value comes from the progress they catalyze ARC Prize 2025 was
Announcing the ARC Prize 2025 Top Score & Paper Award winners The Grand Prize remains unclaimed Our analysis on AGI progress marking 2025 the year of the refinement loop
5
16
68
Congrats to the ARC Prize 2025 winners! The Grand Prize remains unclaimed, but nevertheless 2025 saw remarkable progress on LLM-driven refinement loops, both with "local" models and with commercial frontier models. We also saw the rise of zero-pretraining DL approaches like HRM
Announcing the ARC Prize 2025 Top Score & Paper Award winners The Grand Prize remains unclaimed Our analysis on AGI progress marking 2025 the year of the refinement loop
17
55
542
@jm_alexia ARC Prize 2025 / Paper Award Winner Second Place / SOAR @PourcelJulien, @cedcolas, @pyoudeyer Interview:
2
7
49
Announcing the ARC Prize 2025 Top Score & Paper Award winners The Grand Prize remains unclaimed Our analysis on AGI progress marking 2025 the year of the refinement loop
25
50
319
A huge thanks to @cedcolas @lae_teo @pyoudeyer for their guidance on my application. If you are interested in solving ARC-AGI with evolutionary algorithms (SOAR) or generating diverse coding problems (ACES), check out my work here:
julienp.netlify.app
Theme PaperMod - https://github.com/adityatelange/hugo-PaperMod
0
2
9
Big news: I’m officially a 2025 Google PhD Fellow! 🎓✨ I’m also heading to #NeurIPS2025 in SD! Happy to chat about LLM, code gen, evolutionary algo, open-endedness, self-improvement, enhancing LLM diversity, ARC-AGI, and other subjects. Open to hear about summer internship. ☀️
2
4
17
New research engineer position open in my lab @FlowersINRIA at @Inria on generative AI agentic architectures for educational technologies ! This is for a large scale collaborative project with EvidenceB edTech company. More info here:
docs.google.com
Call for research engineer position, Inria Bordeaux Generative AI agentic architectures for educational technologies Supervision: Pierre-Yves Oudeyer Research group: Flowers AI & CogSci Lab, Inria...
0
4
5
8B model can outperform AlphaEvolve on open optimization problems by scaling compute for inference or test-time RL🚀! ⭕Circle packing: AlphaEvolve (Gemini-2.0-Flash/Pro) : 2.63586276 Ours (DeepSeek-R1-0528-Qwen3-8B) : 2.63598308 🔗in🧵 [1/n]
4
50
186
Come do an internship in the Flowers team! I’ll supervise two projects: one on curious deep-RL agents that learn a self-representation, and one on modelling real students’ learning with LLMs. More details soon , and check out the other internships, they’re super cool!
🚀 New internship positions available in the Flowers AI & CogSci lab !!! Topics: Curiosity-driven deep RL, program synthesis with SWE LLM agents, data science for edTech + other ! Only for students currently enrolled in a master program Info here: https://t.co/Cv49BOyAj0
0
3
7
🚀 New internship positions available in the Flowers AI & CogSci lab !!! Topics: Curiosity-driven deep RL, program synthesis with SWE LLM agents, data science for edTech + other ! Only for students currently enrolled in a master program Info here: https://t.co/Cv49BOyAj0
0
4
13
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.
3
5
24
3 papers from @FlowersINRIA are presented this week at the @ALifeConf , leveraging curiosity-driven AI to explore complex behaviors in #Lenia All first authors are attending the conference if you want to discuss with them Link to interactive websites, papers and code below:
2
8
15
Full talk presenting MAGELLAN is now online ! MAGELLAN opens new possibilties for building open-ended curiosity-driven genAI, by adding metacognitive skills to monitor learning progress in very large goal spaces https://t.co/Sd7r72LwY4
🚀 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: 🔗 https://t.co/uGLBSsOgMn
#OpenEndedLearning #LLM #RL
0
0
1
We are hosting a student researcher for the end of the year with @eyvindn and others in the PI team ( https://t.co/dF9OqTpBv1) ✨ If you are interested in pushing forward NCA research or explore computational life🦎👾, be sure to fill out the form!
github.com
Advance our understanding of how intelligence evolves to develop new technologies for the benefit of humanity and other sentient life - Paradigms of Intelligence Team
looking for a student researcher September-December. working w/ me+@mayalen_etc, and alongside @zzznah+@RandazzoEttore+others in Pi, on either NCAs or Computational Life. must be enrolled in a degree granting program. fill out the interest form by EOW: https://t.co/yuFurFUm9Q
0
2
22
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... 🧵
2
7
31
With the right UX this could be the basis for a really fun and unique game. Code is available!
Synthetic ecosystems that autonomously and continuously evolve in silico 👾 An Alifer dream we pursue with Flow-Lenia ! If you are interested in complex systems with (1) emergent creatures and (2) intrinsic evolutionary dynamics, go check our new paper ! A 🧵
17
7
213
New paper in the Alife journal ! Flow-Lenia: Emergent Evolutionary Dynamics in Mass Conservative Continuous Cellular Automata Congratulations @eplantec and amazing team !
Synthetic ecosystems that autonomously and continuously evolve in silico 👾 An Alifer dream we pursue with Flow-Lenia ! If you are interested in complex systems with (1) emergent creatures and (2) intrinsic evolutionary dynamics, go check our new paper ! A 🧵
0
3
13
🌍 Imagine transforming an LLM into a curiosity-driven AI scientist that generates theories and makes experiments to test them: This is WorldLLM! 🔬 ▶️ Check our new RLDM paper below 👇
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.
0
2
5