MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service

• URL: http://arxiv.org/abs/2605.08527v1
• Date: Fri, 08 May 2026 22:20:24 GMT
• Title: MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
• Abstract summary: MARL (Multi-tenant Asynchronous RL as a Service) is a system for concurrent RL fine-tuning across multiple users and tasks.<n>Our approach is based on two key ideas: (1) sharing a base model across tenants using lightweight LoRA adapters, and (2) a disaggregated asynchronous architecture that decouples rollout generation, environment interaction, and policy training into independently scheduled stages.<n>In multi-task settings, MARL achieves single-task state-of-the-art performance while improving accelerator utilization by up to 4.3x and reducing end-to-end training time by 85%.
• Score: 8.277398548196619
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has significantly improved the reasoning capabilities of large language models (LLMs), particularly in multi-turn agentic settings involving environment interaction like tool use. However, fine-tuning such models remains prohibitively expensive due to high computational requirements, limiting accessibility. We propose MARLaaS (Multi-tenant Asynchronous RL as a Service), a system for concurrent RL fine-tuning across multiple users and tasks. Our approach is based on two key ideas: (1) sharing a base model across tenants using lightweight LoRA adapters, and (2) a disaggregated asynchronous architecture that decouples rollout generation, environment interaction, and policy training into independently scheduled stages. This design enables tasks to progress through the RL pipeline at their own pace in an event-driven manner, reducing cross-task interference, idle time, and end-to-end latency. In multi-task settings (we report up to 32 concurrent tasks), MARLaaS achieves single-task state-of-the-art performance while improving accelerator utilization by up to 4.3x and reducing end-to-end training time by 85%.

Related papers

• DART-FL: Burst-Aware Multitask Federated Learning under Dynamic Inference Demand at the Edge [20.236878186665272]
  Edge intelligence systems increasingly require model training and online inference to coexist.<n>This creates two coupled challenges: sufficient computation must be reserved for inference to maintain service-level objectives.<n>We propose an SLO-aware, demand-driven multitask federated learning framework (DART-FL) that jointly adapts the inference-training resource split and task-level training emphasis.
  arXiv  Detail & Related papers  (2026-08-27T21:03:33Z)
• RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure [49.88201789074532]
  Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning.<n>We present RollArc, a distributed system designed to maximize throughput for multi-task agentic RL on disaggregated infrastructure.
  arXiv  Detail & Related papers  (2025-12-27T11:14:23Z)
• Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony [78.70328630805041]
  ROLL Flash is a system that extends ROLL with native support for asynchronous RL post-training.<n>We show that ROLL Flash significantly improves resource utilization and scalability over synchronous RL post-training.
  arXiv  Detail & Related papers  (2025-10-13T12:41:27Z)
• AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework [76.96794548655292]
  Large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions.<n>Applying reinforcement learning (RL) to train LLM agents in multi-turn, multi-task settings remains challenging due to lack of scalable infrastructure and stable training algorithms.<n>We present the AgentRL framework for scalable multi-turn, multi-task agentic RL training.
  arXiv  Detail & Related papers  (2025-10-05T13:40:01Z)
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation [65.3648667980258]
  Vision-language model (VLM) based GUI agents show promise for automating complex tasks, but face significant challenges in applying reinforcement learning (RL)<n>We propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner.<n>On the OSWorld benchmark, DART-GUI-7B achieves a 42.13% task success rate, a 14.61% absolute gain over the base model, and 7.34% higher than open-source SOTA.
  arXiv  Detail & Related papers  (2025-09-28T13:19:20Z)
• AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training [24.60677187852425]
  Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs)<n>Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks.<n>Task-separated RL frameworks face challenges in complex dataflows and the corresponding resource idling and workload imbalance.<n>We propose AsyncFlow, an asynchronous streaming RL framework for efficient post-training.
  arXiv  Detail & Related papers  (2025-07-02T12:45:34Z)
• StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation [55.75008325187133]
  Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs)<n>StreamRL is designed with disaggregation from first principles to address two types of performance bottlenecks.<n> Experiments show that StreamRL improves throughput by up to 2.66x compared to existing state-of-the-art systems.
  arXiv  Detail & Related papers  (2025-04-22T14:19:06Z)
• Efficient Parallel Reinforcement Learning Framework using the Reactor Model [2.190190313041532]
  Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources. Existing frameworks, such as Ray, are not managing this orchestration efficiently. We have proposed a solution implementing the reactor model, which enforces a set of actors to have a fixed communication pattern.
  arXiv  Detail & Related papers  (2023-12-07T21:19:57Z)
• M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design [95.41238363769892]
  Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. Current MTL regimes have to activate nearly the entire model even to just execute a single task. We present a model-accelerator co-design framework to enable efficient on-device MTL.
  arXiv  Detail & Related papers  (2022-10-26T15:40:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.