English
Related papers

Related papers: Role-Based Fault Tolerance System for LLM RL Post-…

200 papers

Training large language models (LLMs) for pretraining or adapting to new tasks and domains has become increasingly critical as their applications expand. However, as the model and the data sizes grow, the training process presents…

Machine Learning · Computer Science 2024-12-17 Amrutha Varshini Ramesh , Vignesh Ganapathiraman , Issam H. Laradji , Mark Schmidt

LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward…

Computation and Language · Computer Science 2026-05-11 Hengyu Shi , Tianyang Han , Peizhe Wang , Zhiling Wang , Xu Yang , Junhao Su

Embedded systems in safety-critical environments are continuously required to deliver more performance and functionality, while expected to provide verified safety guarantees. Nonetheless, platform-wide software verification (required for…

Systems and Control · Computer Science 2017-05-09 Fardin Abdi , Renato Mancuso , Rohan Tabish , Marco Caccamo

Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the de- sired behavior and constraints of a robot. Usually, these are handcrafted by a expert designer and represent heuristics for relatively…

Artificial Intelligence · Computer Science 2017-03-03 Xiao Li , Cristian-Ioan Vasile , Calin Belta

Recent advances in large language models (LLMs) have highlighted the potential of reinforcement learning with verifiable rewards (RLVR) to enhance reasoning capabilities through extended output sequences. However, traditional RL frameworks…

Computation and Language · Computer Science 2025-07-29 Dong Du , Shulin Liu , Tao Yang , Shaohua Chen , Yang Li

Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. This…

Computation and Language · Computer Science 2023-12-01 Marwa Abdulhai , Isadora White , Charlie Snell , Charles Sun , Joey Hong , Yuexiang Zhai , Kelvin Xu , Sergey Levine

Multi-robot coordination based on large language models (LLMs) has attracted growing attention, since LLMs enable the direct translation of natural language instructions into robot action plans by decomposing tasks and generating high-level…

This paper proposes TRAININGCXL that can efficiently process large-scale recommendation datasets in the pool of disaggregated memory while making training fault tolerant with low overhead. To this end, i) we integrate persistent memory…

Hardware Architecture · Computer Science 2023-01-23 Miryeong Kwon , Junhyeok Jang , Hanjin Choi , Sangwon Lee , Myoungsoo Jung

Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime reconfiguration suffer from long downtimes and degraded…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 ChonLam Lao , Jiaqi Gao , Jiamin Cao , Zhipeng Zhang , Pengcheng Zhang , Jiangfei Duan , Zhilong Zheng , Yu Guan , Yichi Xu , Yong Li , Zhengping Qian , Aditya Akella , Minlan Yu , Ennan Zhai , Dennis Cai , Jingren Zhou

Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental…

Computation and Language · Computer Science 2025-12-19 Bingxiang He , Zekai Qu , Zeyuan Liu , Yinghao Chen , Yuxin Zuo , Cheng Qian , Kaiyan Zhang , Weize Chen , Chaojun Xiao , Ganqu Cui , Ning Ding , Zhiyuan Liu

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient…

Computation and Language · Computer Science 2022-11-01 Yi-Lin Sung , Jaemin Cho , Mohit Bansal

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in…

Machine Learning · Computer Science 2025-02-25 Austin Coursey , Marcos Quinones-Grueiro , Gautam Biswas

In Reward Learning (ReL), we are given feedback on an unknown target reward, and the goal is to use this information to recover it in order to carry out some downstream application, e.g., planning. When the feedback is not informative…

Machine Learning · Computer Science 2025-09-16 Filippo Lazzati , Alberto Maria Metelli

We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of…

Computation and Language · Computer Science 2026-05-20 Minxuan Lv , Tiehua Mei , Tanlong Du , Junmin Chen , Zhenpeng Su , Ziyang Chen , Ziqi Wang , Zhennan Wu , Ruotong Pan , jian Liang , Ruiming Tang , Han Li

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Machine Learning · Computer Science 2026-02-26 Ningyuan Yang , Weihua Du , Weiwei Sun , Sean Welleck , Yiming Yang

The pre-training paradigm plays a key role in the success of Large Language Models (LLMs), which have been recognized as one of the most significant advancements of AI recently. Building on these breakthroughs, code LLMs with advanced…

Software Engineering · Computer Science 2025-04-22 Yuheng Huang , Lei Ma , Keizaburo Nishikino , Takumi Akazaki

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…

Machine Learning · Computer Science 2026-01-21 Quy-Anh Dang , Chris Ngo

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context…

Machine Learning · Computer Science 2025-08-13 Jie Xiao , Changyuan Fan , Qingnan Ren , Alfred Long , Yuchen Zhang , Rymon Yu , Eric Yang , Lynn Ai , Shaoduo Gan

Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there…

Machine Learning · Statistics 2024-06-27 Xiaohong Chen , Zhengling Qi , Runzhe Wan