Reinforcement learning

Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.

6,856 stories · RSS feed

arXiv AI

Sep 15

HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning

arXiv:2609.13739v1 Announce Type: cross Abstract: Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory...

By Hongliang Wei (Harbin Institute of Technology, Alibaba Cloud), Xiaobing Tu (Alibaba Cloud), Yinggui Wang (Alibaba Cloud), Zhengxi Liu (Alibaba Cloud), Rongkun Xue (Alibaba Cloud), Jinkui Ren (Alibaba Cloud), Xiantao Zhang (Alibaba Cloud), Debin Zhao (Harbin Institute of Technology), Xiaopeng Fan (Harbin Institute of Technology)

agents reinforcement-learning benchmarks

arXiv AI

Sep 15

Skill Composition for Legged Robot Reinforcement Learning

arXiv:2609.14647v1 Announce Type: cross Abstract: Robots, and humanoid robots in particular, are increasingly competent at individual behaviors, each obtained by training a specialized controller. A...

By Daniel Gigliotti, Flavio Maiorana, Fabio Patrizi, Luca Iocchi

reinforcement-learning robotics

arXiv AI

Sep 15

Building Legal Reward Models for Grounding and Abstention

arXiv:2609.14739v1 Announce Type: cross Abstract: Large language models are increasingly used in high-stakes domains such as law, where systems must ground their reasoning in retrieved evidence and a...

By Rilton Franzone, Valentin No\"el, Puyu Wang, Philip Torr, Fabio J. Fehr

llms rag reinforcement-learning benchmarks

arXiv AI

Sep 15

Salesforce Koa: An Enterprise Language Model for Agentic Tool Use

arXiv:2609.15066v1 Announce Type: cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcem...

By Zixiang Chen, Sufeng Niu, Yingchi Liu, Wenting Zhao, Akshara Prabhakar, Shubham Mehrotra, Bin Bi, Zhujun Lan, Katherine Tan, Mohammad Ramezanali, Tulika Manoj Awalgaonkar, Monojit Banerjee, Jielin Qiu, Shiva Kumar Pentyala, Zhepeng Cen, Anupam Tripathi, Ali Ziaei, Regunathan Radhakrishnan, Darvish Lee Shadravan, Shelby Heinecke, Sitaram Asur, Silvio Savarese, James Zhu, Phil Mui, Huan Wang

llms agents reinforcement-learning benchmarks

arXiv AI

Sep 15

Refinement-based Flow Policy Optimization

arXiv:2609.15123v1 Announce Type: cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from...

By Bumgeun Park, Hyukjun Yang, Donghwan Lee

diffusion reinforcement-learning multimodal

arXiv AI

Sep 15

AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference

arXiv:2609.15131v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most method...

By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang

llms reinforcement-learning multimodal

arXiv AI

Sep 15

Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials

The study presents a virtual imaging trial framework that uses reinforcement learning to optimize computed tomography (CT) protocols, balancing liver lesion detectability against radiation dose. By training a Proximal Policy Optimization agent on 63 computational human models across 468 parameter combinations, the authors demonstrate that evaluating only eight protocols per patient—about 2% of exhaustive testing—recovers 98.2% of the optimal objective. Conditioning the agent on patient‑specific CT localizer embeddings further improves zero‑simulation recovery by 10.7 percentage points compared to a localizer‑blind policy.

By Jiaqi Zou, David Fenwick, Vahid Tarokh, Nicholas Felice, Jayasai Rajagopal, Anuj Kapadia, Ehsan Samei, Navid NaderiAlizadeh, Ehsan Abadi

llms rag agents computer-vision reinforcement-learning

arXiv AI

Sep 15

Robust and Efficient Communication for Multi-Agent Learning

arXiv:2609.15361v1 Announce Type: cross Abstract: Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messag...

By Rafael Pina, Varuna De Silva, Corentin Artaud

agents reinforcement-learning robotics benchmarks

arXiv AI

Sep 15

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent g...

By Tong Ye, Kunyang Han, Guozhi Wang, Longqiang Luo, Zhifeng Ding, Yongxiang Zhang, Xiaolei Shen, Yuxuan Zhang, Zhuping Zhang, Tao Xu, Yue Pan, Yucheng Zhao, Yupei Hu, Yuanjiang Ouyang, Danfeng Shen, Runqi Lin, Hongda Cai, Zhaoxiong Wang, Mengjia Yan, Yingjie Zhong, Chen Zhou, Zeyu Zhang, Xuwen Zhu, Penggang Shi, Mingcheng Luo, Ziyang Wu, Min Jin, Mingfu Shen, Zairong Xu, Fan Zhang, Hao Wang, Liang Liu, Zhulin Xie, Lijun Yao, Xiao Liang, Liangmin Wen, Liqiang Feng, Feilong Wu, Min Hu, Min Chen, Guanjing Xiong, Xiaohu Ruan, Xiaoxin Chen

agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 15

GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning

arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they rema...

By Zhongyu Wang

rag agents reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Sep 15

Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization

arXiv:2604.13175v2 Announce Type: replace-cross Abstract: Large language models can be aligned with human preferences through offline reinforcement learning (RL) on small labeled datasets. While sing...

By Aadyot Bhatnagar, Peter M{\o}rch Groth, Sebastian Ibarraran, Ali Madani

llms reinforcement-learning benchmarks safety

arXiv AI

Sep 15

Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits

arXiv:2605.29268v3 Announce Type: replace-cross Abstract: LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existi...

By Sixue Xing, Haoyu He, Kerui Wu, Zhuo Yang, Haozheng Luo, Tianfan Fu, Aarthy Nagarajan

llms reinforcement-learning benchmarks

arXiv AI

Sep 15

Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly

arXiv:2609.07534v2 Announce Type: replace-cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sus...

By Yuhan Wang, Yurou Chen, Hongye Jiang, Wenzhao Lian

reinforcement-learning robotics fine-tuning multimodal safety

arXiv Machine Learning

Sep 15

The Filter Metric is Safety-Critical: Phantom Advantages in Group-Relative RL under Shaped Rewards

arXiv:2609.13866v1 Announce Type: new Abstract: Group-relative policy optimization (GRPO and descendants) can discard no-contrast rollout groups through dynamic sampling, while practical implementati...

By Juntao Yu

reinforcement-learning fine-tuning safety

arXiv Machine Learning

Sep 15

Nonparametric Variance-Penalized Actor-Critic: Statistical Inference for Risk-Sensitive Reinforcement Learning

arXiv:2609.14327v1 Announce Type: new Abstract: Variance penalization is a principled approach to risk-sensitive reinforcement learning (RL) that explicitly trades expected return for policy stabilit...

By Saunak Kumar Panda, Tong Li, Yisha Xiang, Ruiqi Liu

reinforcement-learning

arXiv Machine Learning

Sep 15

Selecting k Paths with the Minimum Longest Path Length in the Stochastic Semi-Bandit Setting

arXiv:2609.14557v1 Announce Type: new Abstract: When performing parallel data transmission through a network using multiple paths, it is practically important to minimize the maximum transmission tim...

By Shunsuke Aoki, Atsuyoshi Nakamura

reinforcement-learning

arXiv Machine Learning

Sep 15

HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud

arXiv:2609.14968v1 Announce Type: new Abstract: Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay betwe...

By Tiangang Li, Shi Ying, Xiangbo Tian

reinforcement-learning efficiency

arXiv Machine Learning

Sep 15

What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...

By Lingheng Du, Yiming Tang, Xufeng Duan, Dianbo Liu

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Sep 15

Bellman Policy Optimization

arXiv:2609.15987v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy...

By Zhuoqing Song, Haotian Xu, Xikun Zhang, Lidong Bing

llms reinforcement-learning benchmarks

arXiv Machine Learning

Sep 15

GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo

arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...

By Amal Dev Haridevan, Junjie Kang, Jinjun Shan

agents reinforcement-learning robotics fine-tuning efficiency benchmarks

Get the daily briefing