# LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training

arXiv: https://arxiv.org/abs/2505.24034 · HTML: https://mlsanity.com/paper/2505.24034/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 68 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 48)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)

## Built on by (most cited first, 30 of 42)

- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [Prompt Curriculum Learning for Efficient LLM Post-Training](https://mlsanity.com/paper/2510.01135/) (2025)
- [Laminar: A Scalable Asynchronous RL Post-Training Framework](https://mlsanity.com/paper/2510.12633/) (2025)
- [APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation](https://mlsanity.com/paper/2509.18521/) (2025)
- [Single-stream Policy Optimization](https://mlsanity.com/paper/2509.13232/) (2025)
- [Introducing LongCat-Flash-Thinking: A Technical Report](https://mlsanity.com/paper/2509.18883/) (2025)
- [Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony](https://mlsanity.com/paper/2510.11345/) (2025)
- [DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training](https://mlsanity.com/paper/2604.26256/) (2026)
- [A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation](https://mlsanity.com/paper/2512.06547/) (2025)
- [Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs](https://mlsanity.com/paper/2602.17616/) (2026)
- [Efficient RL Training for LLMs with Experience Replay](https://mlsanity.com/paper/2604.08706/) (2026)
- [Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding](https://mlsanity.com/paper/2604.26779/) (2026)
- [LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs](https://mlsanity.com/paper/2510.16552/) (2025)
- [Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning](https://mlsanity.com/paper/2602.06107/) (2026)
- [Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training](https://mlsanity.com/paper/2605.26606/) (2026)
- [Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models](https://mlsanity.com/paper/2606.08446/) (2026)
- [GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning](https://mlsanity.com/paper/2508.17850/) (2025)
- [TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training](https://mlsanity.com/paper/2604.09107/) (2026)
- [Libra: Efficient Resource Management for Agentic RL Post-Training](https://mlsanity.com/paper/2606.03077/) (2026)
- [Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing](https://mlsanity.com/paper/2509.08721/) (2025)
- [Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO](https://mlsanity.com/paper/2511.09780/) (2025)
- [Role-Based Fault Tolerance System for LLM RL Post-Training](https://mlsanity.com/paper/2512.22492/) (2025)
- [Rollout-Level Advantage-Prioritized Experience Replay for GRPO](https://mlsanity.com/paper/2606.04560/) (2026)
- [Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training](https://mlsanity.com/paper/2606.11867/) (2026)
- [Staleness-Learning Rate Scaling Laws for Asynchronous RLHF](https://mlsanity.com/paper/2607.01083/) (2026)
- [Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning](https://mlsanity.com/paper/2511.18871/) (2025)
- [CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production](https://mlsanity.com/paper/2603.01973/) (2026)
- [AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models](https://mlsanity.com/paper/2603.18464/) (2026)
- [MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service](https://mlsanity.com/paper/2605.08527/) (2026)
- [F-TIS: Harnessing Diverse Models in Collaborative GRPO](https://mlsanity.com/paper/2605.22537/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging to develop an efficient RL framework that reliably manages policy models with hundreds to thousands of billions of parameters. In this paper, we present LlamaRL, a fully distributed, asynchronous RL framework optimized for efficient training of large-scale LLMs with various model sizes (8B, 70B, and 405B parameters) on GPU clusters ranging from a handful to thousands of devices. LlamaRL introduces a streamlined, single-controller architecture built entirely on native PyTorch, enabling modularity, ease of use, and seamless scalability to thousands of GPUs. We also provide a theoretical analysis of LlamaRL's efficiency, including a formal proof that its asynchronous design leads to strict RL speed-up. Empirically during the Llama 3 post-training, by leveraging best practices such as colocated model offloading, asynchronous off-policy training, and distributed direct memory access for weight synchronization, LlamaRL achieves significant efficiency gains -- up to 10.7x speed-up compared to DeepSpeed-Chat-like systems on a 405B-parameter policy model. Furthermore, the efficiency advantage continues to grow with increasing model scale, demonstrating the framework's suitability for future large-scale RL training.