Paper
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
Authors
Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han, Jian Hu, Zhenghui Jin, Yuchi Zhang, Shizhe Diao, Ximing Lu, Binfeng Xu, Zhiding Yu, Jan Kautz, Yi Dong
Abstract
Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and maintain. Under the rollout-as-a-service philosophy, we present ProRL Agent , a scalable infrastructure that serves the full agentic rollout lifecycle through an API service. ProRL Agent also provides standardized and extensible sandbox environments that support diverse agentic tasks in rootless HPC settings. We validate ProRL Agent through RL training on software engineering, math, STEM, and coding tasks. ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.18815v1</id>\n <title>ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents</title>\n <updated>2026-03-19T12:08:51Z</updated>\n <link href='https://arxiv.org/abs/2603.18815v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.18815v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires generating large numbers of sandboxed rollout trajectories, and existing infrastructures often couple rollout orchestration with the training loop, making systems hard to migrate and maintain. Under the rollout-as-a-service philosophy, we present ProRL Agent , a scalable infrastructure that serves the full agentic rollout lifecycle through an API service. ProRL Agent also provides standardized and extensible sandbox environments that support diverse agentic tasks in rootless HPC settings. We validate ProRL Agent through RL training on software engineering, math, STEM, and coding tasks. ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-19T12:08:51Z</published>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Hao Zhang</name>\n </author>\n <author>\n <name>Mingjie Liu</name>\n </author>\n <author>\n <name>Shaokun Zhang</name>\n </author>\n <author>\n <name>Songyang Han</name>\n </author>\n <author>\n <name>Jian Hu</name>\n </author>\n <author>\n <name>Zhenghui Jin</name>\n </author>\n <author>\n <name>Yuchi Zhang</name>\n </author>\n <author>\n <name>Shizhe Diao</name>\n </author>\n <author>\n <name>Ximing Lu</name>\n </author>\n <author>\n <name>Binfeng Xu</name>\n </author>\n <author>\n <name>Zhiding Yu</name>\n </author>\n <author>\n <name>Jan Kautz</name>\n </author>\n <author>\n <name>Yi Dong</name>\n </author>\n </entry>"
}