arXiv Machine Learning

Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference

arXiv:2608. 06025v1 Announce Type: new Abstract: In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations.

arXiv Machine Learning

Jul 21

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training

arXiv:2604. 26256v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline.

By Tianhao Hu, Xiangcheng Liu, Yuchun Miao, Youshao Xiao, Hongyu Zang, Yang Zheng, Xuan Huang, Jinrui Ding, Yufei Zhang, Yu Yang, Yi-Kai Zhang, Yueqing Sun, Chengcheng Han, Xiandi Ma, Wei Wang, Qi Gu, Yerui Sun, Yuchen Xie, Xunliang Cai

llms agents reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jul 10

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

arXiv:2601. 22448v2 Announce Type: replace Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when.

By Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao, Priyanka Nigam, Bing Yin, Lihong Li, Yangqiu Song

llms reinforcement-learning benchmarks

arXiv AI

Jul 7

Adaptive Inference Batching using Policy Gradients

arXiv:2607. 05272v1 Announce Type: cross Abstract: Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching policies that require manual tuning and cannot adapt to shifting traffic.

By Ruslan Sharifullin

agents reinforcement-learning efficiency

arXiv AI

Jun 11

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control

arXiv:2605. 26418v2 Announce Type: replace-cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help?

By Guilin Zhang, Chuanyi Sun, Kai Zhao, Shahryar Sarkani, John Fossaceca

agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 5

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

arXiv:2602. 06932v5 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem.

By Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou, Zelei Shao, Yubo Wang, Yinghui Liu, Qingyang Wu, Avner May, Sri Yanamandra, Ce Zhang, Tri Dao, Percy Liang, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu

llms reinforcement-learning

arXiv AI

1d ago

ClawGym II: Exploring Black-Box RL on Agent Harness

arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.

By Huatong Song, Fei Bai, Ming Yang, Renyuan Li, Jia Deng, Jujie He, Zhange Zhang, Daixuan Cheng, Yan Xing, Qi Yun, Xuxing Chen, Danyang Li, Feng Chang, Chuan Hao, Ran Tao, Jian Yang, Bryan Dai, Wayne Xin Zhao, Mingjie Tang, Ji-Rong Wen

llms agents reinforcement-learning

arXiv Machine Learning

Aug 12

TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling

arXiv:2608. 10402v1 Announce Type: new Abstract: Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times.

By Yanyu Ren, Xizheng Wang, Xiao Liu, Bowen Lv, Hanchen Zhang, Shudan Zhang, Hanyu Lai, Shuai Wang, Li Chen, Dan Li, Jie Tang

llms agents reinforcement-learning efficiency multimodal

arXiv Machine Learning

Jul 7

Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning

arXiv:2607. 04577v1 Announce Type: new Abstract: Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct.

By Saurabhsingh Rajput, Tushar Sharma

reinforcement-learning fine-tuning efficiency

arXiv AI

Aug 6

Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimality

arXiv:2510. 17709v2 Announce Type: replace-cross Abstract: Training Reinforcement Learning (RL) policies using simulation models before deployment in real-world environments is a common strategy when real-world interaction is expensive.

By Akhil S Anand, Shambhuraj Sawant, Paavo Parmas, Jasper Hoffmann, Dirk Reinhardt, Sebastien Gros

reinforcement-learning robotics

arXiv AI

Jul 21

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

arXiv:2607. 17299v1 Announce Type: cross Abstract: Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL).

By Ryan Xu, Atlas Zhao, David Bao, Frank Du

agents reinforcement-learning efficiency

arXiv AI

Jun 11

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

arXiv:2606. 11440v1 Announce Type: new Abstract: Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features.

By Ahasan Kabir, Jiaqi Xue, Mengxin Zheng, Qian Lou

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 11

DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference

arXiv:2608. 08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference.

By Asaad Althoubi

llms reinforcement-learning efficiency benchmarks

Related stories