arXiv Machine Learning

rl-triton: High-Performance Triton GPU Kernels for Reinforcement Learning Credit Assignment

arXiv:2608. 17641v1 Announce Type: new Abstract: We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton.

arXiv Machine Learning

Jun 16

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.

By Jiamin Xu, Kyra Gan

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 17

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

arXiv:2607. 14952v1 Announce Type: new Abstract: A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment.

By Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao, Harry Zhang, Irvine Lu, Nolan Ho, Lucian Li, Andrew Lei, Cleon Cheng, Steven Chiang, Yihang Zeng, Di Zhang, Rio Yang, Kaijie Chen, Andrew Chen, Pony Ma, Weizhong Zhang, Cheng Jin

agents reinforcement-learning

arXiv AI

Jun 29

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

arXiv:2606. 27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal.

By Arnav Raj

reinforcement-learning safety

arXiv Machine Learning

4d ago

Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

arXiv:2608. 14498v1 Announce Type: new Abstract: Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions.

By Hanfeng Lu, Tianyu Feng, Suyi Li, Yuheng Zhao, Wei Gao, Shaopan Xiong, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Wei Wang

llms agents reinforcement-learning robotics multimodal

arXiv AI

Jun 18

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arXiv:2606. 19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs.

By Ruiqi Lai, Dakai An, Wei Gao, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Dmitrii Ustiugov, Wei Wang

llms diffusion computer-vision reinforcement-learning

arXiv Machine Learning

Jul 20

DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts

arXiv:2605. 15422v3 Announce Type: replace Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard FlashAttention replicates all P prompt tokens N times across both forward and backward passes -- duplicating compute and memory on identical hidden states.

By Jiading Gai, Shuai Zhang, Xiang Song, Bernie Wang, George Karypis

reinforcement-learning efficiency

arXiv AI

Jun 16

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

arXiv:2606. 16497v1 Announce Type: cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective.

By Dayuan Fu, Mohan Jiang, Tongyu Wang, Dian Yang, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Li

llms rag agents nlp reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 4

MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

arXiv:2606. 04847v1 Announce Type: cross Abstract: Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code.

By Kun Cheng, Songshuo Lu, Sicong Liao, Tankun Li, Yafei Zhang, Dong Yang, Qiheng Lv, Hua Wang, Zhi Chen, Yaohua Tang

llms reinforcement-learning fine-tuning

Hugging Face Trending Papers

Jul 23

Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code.

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 4

LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation

arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.

By Tankun Li, Zhi Chen, Yaohua Tang

llms reinforcement-learning efficiency benchmarks safety

arXiv AI

Jul 17

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.

By Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao Yu, Guodong Yang, Liping Zhang

llms rag agents benchmarks

arXiv AI

Jul 17

A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi

arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.

By A. C. Opus, J. Q. Lu

rag multimodal benchmarks

Related stories