# Command A: An Enterprise-Ready Large Language Model

arXiv: https://arxiv.org/abs/2504.00698 · HTML: https://mlsanity.com/paper/2504.00698/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2025.

## Built on by (most cited first, 30 of 59)

- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2504.12501/) (2025)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL](https://mlsanity.com/paper/2505.20315/) (2025)
- [MergeBench: A Benchmark for Merging Domain-Specialized LLMs](https://mlsanity.com/paper/2505.10833/) (2025)
- [WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training](https://mlsanity.com/paper/2507.17634/) (2025)
- [Weight Decay may matter more than muP for Learning Rate Transfer in Practice](https://mlsanity.com/paper/2510.19093/) (2025)
- [Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light](https://mlsanity.com/paper/2504.16922/) (2025)
- [World Modelling Improves Language Model Agents](https://mlsanity.com/paper/2506.02918/) (2025)
- [Hybrid Architectures for Language Models: Systematic Analysis and Design Insights](https://mlsanity.com/paper/2510.04800/) (2025)
- [Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling](https://mlsanity.com/paper/2507.14783/) (2025)
- [Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures](https://mlsanity.com/paper/2510.24081/) (2025)
- [Multilingual Performance Biases of Large Language Models in Education](https://mlsanity.com/paper/2504.17720/) (2025)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset](https://mlsanity.com/paper/2505.19978/) (2025)
- [Continually Adding New Languages to Multilingual Language Models](https://mlsanity.com/paper/2509.11414/) (2025)
- [Composer: A Search Framework for Hybrid Neural Architecture Design](https://mlsanity.com/paper/2510.00379/) (2025)
- [TROLL: Trust Regions improve Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2510.03817/) (2025)
- [Unlocking Reasoning Capability on Machine Translation in Large Language Models](https://mlsanity.com/paper/2602.14763/) (2026)
- [Scale-invariant Attention](https://mlsanity.com/paper/2505.17083/) (2025)
- [Is Extending Modality The Right Path Towards Omni-Modality?](https://mlsanity.com/paper/2506.01872/) (2025)
- [A State-of-the-Art SQL Reasoning Model using RLVR](https://mlsanity.com/paper/2509.21459/) (2025)
- [A Systematic Study of In-the-Wild Model Merging for Large Language Models](https://mlsanity.com/paper/2511.21437/) (2025)
- [Characterization and Mitigation of Training Instabilities in Microscaling Formats](https://mlsanity.com/paper/2506.20752/) (2025)
- [Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance](https://mlsanity.com/paper/2511.13254/) (2025)
- [SimMerge: Learning to Select Merge Operators from Similarity Signals](https://mlsanity.com/paper/2601.09473/) (2026)
- [ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs](https://mlsanity.com/paper/2602.13274/) (2026)
- [ShiQ: Bringing back Bellman to LLMs](https://mlsanity.com/paper/2505.11081/) (2025)
- [Controlling Language Confusion in Multilingual LLMs](https://mlsanity.com/paper/2505.19116/) (2025)
- [Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors](https://mlsanity.com/paper/2506.14794/) (2025)

## Abstract (arXiv)

In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised and multilingual-capable model, with support for 23 languages of global business, and a novel hybrid architecture balancing efficiency with top of the range performance. It offers best-in-class Retrieval Augmented Generation (RAG) capabilities with grounding and tool use to automate sophisticated business processes. These abilities are achieved through a decentralised training approach, including self-refinement algorithms and model merging techniques. We also include results for Command R7B which shares capability and architectural similarities to Command A. Weights for both models have been released for research purposes. This technical report details our original training pipeline and presents an extensive evaluation of our models across a suite of enterprise-relevant tasks and public benchmarks, demonstrating excellent performance and efficiency.