Research Open Source CV

Hi, I’m Corentin, a Research Engineer at Huawei Noah's Ark Lab Paris, working on LLMs, AutoML and RL under the supervision of Balázs Kégl.

Prior to that, I was a Research Engineer at Inria in the Flowers lab, where I developed multi-agent systems, supervised by Clément Moulin Frier. During my MSc in Computer and Cognitive Sciences at ENSC, I also interned at Connectiv-IT as a Data Scientist, and at Inria Flowers doing Reinforcement Learning research.

Among a lot of other things, I love sports and play volley-ball at a national level (bronze medal in the 2023 French University Championship!).

Contact: corentin.lger@gmail.com

Avatar

Research

You can check my Google Scholar for more details about the publications.

llm_persuasion

Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies
A J Reedi, C Léger, J Pourcel, L Gaven, Perrine Charriau, G Pourcel
MTI-LLM @ NeurIPS, 2025 

@article{reedi2025optimizing,
  title={Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies},
  author={Reedi, Aksel Joonas and L{\'e}ger, Corentin and Pourcel, Julien and Gaven, Loris and Charriau, Perrine and Pourcel, Guillaume},
  journal={arXiv preprint arXiv:2510.05909},
  year={2025}
}
llm_hps

In-Context Meta-Learning with Large Language Models for Automated Model and Hyperparameter Selection
Y Attia El Hili, A Thomas, A Benechehab, C Léger, C Ancourt, B Kégl
LLM-eval @ NeurIPS, 2025 

@inproceedings{el2025context,
   title={In-Context Meta-Learning with Large Language Models for Automated Model and Hyperparameter Selection},
   author={El Hili, Youssef Attia and Thomas, Albert and Benechehab, Abdelhakim and L{\'e}ger, Corentin and Ancourt, Corinne and K{\'e}gl, Bal{\'a}zs},
   booktitle={NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling}
}
telephonellm

When LLMs Play the Telephone Game: Cumulative Changes and Attractors in Iterated Cultural Transmissions
J Perez, G Kovač, C Léger, C Colas, G Molinaro, M Derex, PY Oudeyer, C Moulin-Frier
ICLR, 2025 

@inproceedings{perez2025llms,
   title={When LLMs play the telephone game: Cultural attractors as conceptual tools to evaluate LLMs in multi-turn settings},
   author={Perez, J{\'e}r{\'e}my and Kova{\v{c}}, Grgur and L{\'e}ger, Corentin and Colas, C{\'e}dric and Molinaro, Gaia and Derex, Maxime and Oudeyer, Pierre-Yves and Moulin-Frier, Cl{\'e}ment},
   booktitle={The Thirteenth International Conference on Learning Representations},
   year={2025}
}
llm_culture

Cultural evolution in populations of Large Language Models
J Perez, C Léger, M Ovando-Tellez, C Foulon, J Dussauld, PY Oudeyer, C Moulin-Frier
arXiv, 2024 

@article{perez2024cultural,
   title={Cultural evolution in populations of Large Language Models},
   author={Perez, J{\'e}r{\'e}my and L{\'e}ger, Corentin and Ovando-Tellez, Marcela and Foulon, Chris and Dussauld, Joan and Oudeyer, Pierre-Yves and Moulin-Frier, Cl{\'e}ment},
   journal={arXiv preprint arXiv:2403.08882},
   year={2024}
}
er-mrl

Evolving reservoirs for Meta Reinforcement Learning
*C Léger, *G Hamon, E Nisioti, X Hinaut, C Moulin-Frier
EvoStar [Long Talk], 2024 

@inproceedings{leger2024evolving,
   title={Evolving Reservoirs for Meta Reinforcement Learning},
   author={L{\'e}ger, Corentin and Hamon, Gautier and Nisioti, Eleni and Hinaut, Xavier and Moulin-Frier, Cl{\'e}ment},
   booktitle={International Conference on the Applications of Evolutionary Computation (Part of EvoStar)},
   pages={36--60},
   year={2024},
   organization={Springer}
}
symbolic-rl

Early Empirical Results on Reinforcement Symbolic Learning
W Radji, C Léger, L Bardisbanian
HAL Inria, 2023 

@phdthesis{radji2023early,
   title={Early Empirical Results on Reinforcement Symbolic Learning},
   author={Radji, Waris and L{\'e}ger, Corentin and Bardisbanian, Lucas},
   year={2023},
   school={Inria \& Labri, Univ. Bordeaux}
}

Open Source

Here is a list of open source projects I contributed to, you can check my GitHub profile for more details.

Vivarium Star : Multi-agent Jax simulator in a 2D physics-based world. see more

LLM-Culture Star : Simulating text evolution in networks of LLMs. see more

KanRL Star : Combine RL and Kolmogorov-Arnold Networks (KANs). see more

I also fixed a few issues in the Stable-Baselines3 Reinforcement Learning library, and created a tutorial for parallelized hyperparameter search on remote clusters in ReservoirPy.

Teaching

UPF

January 2025 - Teaching assistant, Introduction to multi-agent systems (9h)

Hackathons

🧠 Hack1Robo 2024 (first place): Optimized persuasion skills of LLMs in debate tournaments via prompt evolution. Used a Quality Diversity method to evolve the strategies of debaters LLMs.

🤖 Hugging Face LeRobot: Assembled a robotic arm and created a real-world RL environment for objects manipulation. Trained the robotic arm using both Behavioral cloning and online Reinforcement Learning.

📚 Hack1Robo 2023: Simulated text evolution in populations of LLMs, and analyze the resulting dynamics (inspired by works in cultural evolution). This later led to the publication of 2 papers.

🧬 Inria Hackatech 2023: Optimized multi-LLM agent systems strategies via prompt evolution. Reached GPT-4 level on math tasks with evolved systems of GPT-3.5 agents. This led to a startup creation: Ebiose.