Search arXivSearch

arXiv · 2506.10910

Magistral

Mistral-AI·:·Abhinav Rastogi·Albert Q. Jiang·Andy Lo·Gabrielle Berrada·Guillaume Lample·Jason Rute·Joep Barmentlo·Karmesh Yadav·Kartik Khandelwal·Khyathi Raghavi Chandu·Léonard Blier·Lucile Saulnier·Matthieu Dinot·Maxime Darrin·Neha Gupta·Roman Soletskyi·Sagar Vaze·Teven Le Scao·Yihan Wang·Adam Yang·Alexander H. Liu·Alexandre Sablayrolles·Amélie Héliou·Amélie Martin·Andy Ehrenberg·Anmol Agarwal·Antoine Roux·Arthur Darcet·Arthur Mensch·Baptiste Bout·Baptiste Rozière·Baudouin De Monicault·Chris Bamford·Christian Wallenwein·Christophe Renaudin·Clémence Lanfranchi·Darius Dabert·Devon Mizelle·Diego de las Casas·Elliot Chane-Sane·Emilien Fugier·Emma Bou Hanna·Gauthier Delerce·Gauthier Guinet·Georgii Novikov·Guillaume Martin·Himanshu Jaju·Jan Ludziejewski·Jean-Hadrien Chabran·Jean-Malo Delignon·Joachim Studnia·Jonas Amar·Josselin Somerville Roberts·Julien Denize·Karan Saxena·Kush Jain·Lingxiao Zhao·Louis Martin·Luyu Gao·Lélio Renard Lavaud·Marie Pellat·Mathilde Guillaumin·Mathis Felardos·Maximilian Augustin·Mickaël Seznec·Nikhil Raghuraman·Olivier Duchenne·Patricia Wang·Patrick von Platen·Patryk Saffer·Paul Jacob·Paul Wambergue·Paula Kurylowicz·Pavankumar Reddy Muddireddy·Philomène Chagniot·Pierre Stock·Pravesh Agrawal·Romain Sauvestre·Rémi Delacourt·Sanchit Gandhi·Sandeep Subramanian·Shashwat Dalal·Siddharth Gandhi·Soham Ghosh·Srijan Mishra·Sumukh Aithal·Szymon Antoniak·Thibault Schueller·Thibaut Lavril·Thomas Robert·Thomas Wang·Timothée Lacroix·Valeriia Nemychnikova·Victor Paltz·Virgile Richard·Wen-Ding Li·William Marshall·Xuanyu Zhang

Abstract

We introduce Magistral, Mistral's first reasoning model and our own scalable reinforcement learning (RL) pipeline. Instead of relying on existing implementations and RL traces distilled from prior models, we follow a ground up approach, relying solely on our own models and infrastructure. Notably, we demonstrate a stack that enabled us to explore the limits of pure RL training of LLMs, present a simple method to force the reasoning language of the model, and show that RL on text data alone maintains most of the initial checkpoint's capabilities. We find that RL on text maintains or improves multimodal understanding, instruction following and function calling. We present Magistral Medium, trained for reasoning on top of Mistral Medium 3 with RL alone, and we open-source Magistral Small (Apache 2.0) which further includes cold-start data from Magistral Medium.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mistral-AI, :, Abhinav Rastogi, Albert Q. Jiang, Andy Lo, Gabrielle Berrada, Guillaume Lample, Jason Rute, Joep Barmentlo, Karmesh Yadav, Kartik Khandelwal, Khyathi Raghavi Chandu, Léonard Blier, Lucile Saulnier, Matthieu Dinot, Maxime Darrin, Neha Gupta, Roman Soletskyi, Sagar Vaze, Teven Le Scao, Yihan Wang, Adam Yang, Alexander H. Liu, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Andy Ehrenberg, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clémence Lanfranchi, Darius Dabert, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jean-Hadrien Chabran, Jean-Malo Delignon, Joachim Studnia, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Kush Jain, Lingxiao Zhao, Louis Martin, Luyu Gao, Lélio Renard Lavaud, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Maximilian Augustin, Mickaël Seznec, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patrick von Platen, Patryk Saffer, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavankumar Reddy Muddireddy, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Romain Sauvestre, Rémi Delacourt, Sanchit Gandhi, Sandeep Subramanian, Shashwat Dalal, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Thibault Schueller, Thibaut Lavril, Thomas Robert, Thomas Wang, Timothée Lacroix, Valeriia Nemychnikova, Victor Paltz, Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang. 2025-06-12. Magistral. https://arxiv.org/abs/2506.10910

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

LiSeCo: Linear Semantic Control for Language Generation

The prevalence of Large Language Models (LLMs) in critical applications highlights the need for controlled language generation methods that are both computationally efficient and enjoy performance guarantees. To address this need, we use a common model of concept semantics as linearly represented in an LLM's latent space. In particular, we take the view that natural language generation traces a trajectory in this continuous semantic space, realized by the language model's hidden activations. This view permits a control-theoretic treatment of text generation in latent space, in which we propose Linear Semantic Control (LiSeCo), a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings. In particular, we propose to directly intervene, in an online fashion, the activations of the token that is being generated in embedding space. Crucially, LiSeCo does not simply steer activations towards a desirable region. Instead, it relies on classical techniques from control theory to precisely control activations in a context-dependent way, and guarantees that they are brought into a specific pre-defined region of embedding space that corresponds to allowed semantics. The intervention is computed in closed form according to an optimal controller formulation, minimally impacting generation time. This control of the activations in embedding space allows for fine-grained steering of attributes of the generated sequence. We demonstrate that our approach is effective on different tasks -- toxicity, sentiment, and language (English/Spanish) steering -- while maintaining text quality.

cs.CL

VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark

We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu-bench.github.io/

cs.CL

RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning

Machine unlearning for large language models (LLMs) remains challenging because full retraining is costly, while approximate methods often struggle to remove targeted behaviors without degrading retained utility, especially under limited post-deployment supervision. We consider a practical PEFT setting for targeted behavioral contamination removal with a small forget set, a limited retain buffer, and LoRA-only updates, and propose RapidUn, an influence-guided framework that converts cross-sample influence estimates into fixed sample-specific weights for weighted LoRA unlearning. Across Llama-3-8B on Dolly-15k and Alpaca-57k, with cross-model validation on Mistral-7B + Dolly-15k, RapidUn achieves lower seen-trigger and OOD-trigger-family ASR than Fisher, GA, and LoReUn while maintaining competitive clean utility. On Llama-3-8B + Alpaca-57k, it achieves a 77x wall-clock speedup over the clean-corpus LoRA retraining reference. Complementary TOFU, semantic LLM-judge, and IFEval evaluations further support the effectiveness of influence-guided sample reweighting beyond the controlled trigger benchmark.

cs.CL