2025
- Boulet, T., Hinaut, X., Moulin-Frier, C. Software Engineering Agents for Embodied Controller Generation: A Study in Minigrid Environments. EfficientReasoning@NeurIPS 2025. https://inria.hal.science/hal-05330526
- Coignion, T., Quinton, C., Rouvoy, R. When Faster Isn’t Greener: The Hidden Costs of LLM-Based Code Optimization. ASE 2025. https://hal.archives-ouvertes.fr/hal-05227453
- Döderlein, J.B., Kouadio, N.H., Acher, M., Khelladi, D.E., Combemale, B. Piloting Copilot, Codex, and StarCoder2: Hot temperature, cold prompts, or black magic? Journal of Systems and Software 2025. https://arxiv.org/abs/2210.14699
- Pourcel, J., Colas, C., Oudeyer, P.Y. Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI. ICML 2025. https://arxiv.org/abs/2507.14172
- Reux, C., Acher, M., Khelladi, D.E., Barais, O., Quinton, C. LLM Code Customization with Visual Results: A Benchmark on TikZ. EASE 2025. https://hal.archives-ouvertes.fr/hal-05049250
- Spieker, H., Matricon, T., Belmecheri, N., Betten, J.E., Le Bartz Lyan, G., Borges, H., Mazouni, Q., Gross, D., Gotlieb, A., Acher, M. Prompting for Performance: Exploring LLMs for Configuring Software. ICTAI 2025. https://arxiv.org/abs/2507.09790
- Stoskopf, T., Cohen, C., Tabareau, N., Babel-formal: Translation of Proofs between Lean and Rocq. MathAI@NeurIPS 2025. https://hal.science/hal-05342510/
- Stoskopf, T., Viennot, J., Cohen, C., LLM4Docq: Bootstrapping Documentation for MathComp with LLMs and Expert Feedback, Rocqshop@ITP 2025. https://coq-workshop.gitlab.io/2025/files/EA9.pdf
- Viennot, J., Baudart, G., Gallego Arias, E.J., Lelarge, M. MiniF2F in Rocq: Automatic Translation Between Proof Assistants–A Case Study. MathAI@NeurIPS 2025. https://arxiv.org/abs/2503.04763
- Zine, N., Quinton, C., Rouvoy, R. LLM-based Co-Evolution of Configurable Software Systems. SPLC 2025. https://hal.archives-ouvertes.fr/hal-05090995
- Acher, M. Une meilleure IA pour développer du code, Inria Communication 2025, https://www.inria.fr/fr/meilleure-ia-developper-code-diverse
- Baudart, G. Faire communiquer un modèle de langage et un assistant de preuve, Blog Binaire, 2025 https://www.lemonde.fr/blog/binaire/2025/05/23/faire-communiquer-un-modele-de-langage-et-un-assistant-de-preuve/
2024
- Pourcel, G., Carta, T., Kovač, G., Oudeyer, P.Y. Autotelic LLM-based exploration for goal-conditioned RL. IMOL@NeurIPS 2024. https://inria.hal.science/hal-04861896
- Pourcel, J., Colas, C., Molinaro, G., Oudeyer, P.Y., Teodorescu, L. Aces: generating diverse programming puzzles with autotelic language models and semantic descriptors. NeurIPS 2024. https://arxiv.org/abs/2310.10692
- Teodorescu, L., Baudart, G., Gallego Arias, E.J., Lelarge, M. NLIR: Natural Language Intermediate Representation for Mechanized Theorem Proving. MathAI@NeurIPS 2024. https://hal.science/hal-04886208