• Home
• People
• Jobs
• Visit
• Thesis Topics
• Publications
• Conference Rankings
• Research
• Bcast
• Teaching
• Contact

SPONSORS

COLLABORATIONS

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

M. Besta, L. Schmidt, P. Pang, P. Okanovic, R. Gerstenberger, T. Hoefler:
	RPEG: Training Reasoning Language Models Scalably and Cost-Effectively (arXiv:2611.09207. Nov. 2026) Abstract Reinforcement learning (RL) is now central to training Reasoning Language Models (RLMs), but RLM pipelines are difficult to scale and costly to run because each RL step couples multiple large models, heterogeneous stages, cross-step state, and complex asynchronous dependencies. Existing systems typically optimize only parts of this design space. We address this complexity by jointly optimizing the pipeline structure as well as its execution using a novel data-centric graph intermediate representation called RLM Pipeline Execution Graph (RPEG). RPEG exposes structural choices such as bounded asynchrony and actor-critic sharing together with execution optimizations such as stage fusion, fine-grained scheduling, and multi-dimensional model parallelism. It is coupled with a comprehensive analytical performance model for RLM training, jointly capturing compute, communication, memory, and hierarchical rack-, node-, and GPU-level effects. Across systems with up to 256 GH200 GPUs, our distributed runtime engine implementing RPEG improves performance by up to 2x over ReaL and reduces step latency by up to 2.48x over verl, while increasing hardware utilization by up to 30%. Overall, RPEG provides a graph-driven foundation for next-generation training pipelines for frontier reasoning LLMs. Documents download article: access preprint on arxiv:
	BibTeX
@article{besta2026rpeg,   author={Maciej Besta and Leonard Schmidt and Pierre Pang and Patrik Okanovic and Robert Gerstenberger and Torsten Hoefler},   title={{RPEG: Training Reasoning Language Models Scalably and Cost-Effectively}},   journal={arXiv:2611.09207},   year={2026},   month={11},   doi={10.48550/arXiv.2611.09207}, }