Reinforcement learning

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

7,110 stories · RSS feed

arXiv AI

Jul 7

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

arXiv:2603. 27044v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space.

By Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jul 7

AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference

arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.

By Sadra Saremi

llms agents reinforcement-learning efficiency

arXiv Machine Learning

Jul 7

RL Forgets! Towards Continual Policy Optimization

arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.

By Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 7

Fitted Occupancy-Ratio Evaluation without Bellman Completeness

arXiv:2607. 05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation.

By Lars van der Laan, Nathan Kallus

reinforcement-learning

arXiv AI

Jul 7

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

arXiv:2602. 21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.

By Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Renliang Sun, Alexander Taylor, Yanqiao Zhu, Jason Cong, Yizhou Sun, Wei Wang

llms agents reinforcement-learning

arXiv AI

Jul 7

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

arXiv:2510. 08048v4 Announce Type: replace-cross Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion.

By Jianhui Yang, Yiming Jin, Pengkun Jiao, Chenhe Dong, Zerui Huang, Shaowei Yao, Xiaojiang Zhou, Dan Ou, Haihong Tang

llms reinforcement-learning fine-tuning

arXiv AI

Jul 7

MentalThink: Shaping Thoughts in Mental SVG World

arXiv:2607. 03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization.

By Kangheng Lin, Jisheng Yin, Dingming Li, En Yu, Yana Wei, Han Zhou, Liang Zhao, Hongyu Zhou, Hongbo Peng, Jianjian Sun, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Jingyu Wang

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 7

A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective

arXiv:2503. 23650v2 Announce Type: replace Abstract: Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD).

By Zhuoren Li, Guizhe Jin, Ran Yu, Weiqi Zhang, Zhiwen Chen, Nan Li, Lu Xiong, Ilya Kolmanovsky, Dimitar Filev, Bo Leng, Jia Hu

agents reinforcement-learning robotics

arXiv Machine Learning

Jul 7

Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

arXiv:2408. 09112v2 Announce Type: replace Abstract: Reinforcement learning policies parametrized by deep neural networks have achieved strong performance for continuous control, yet even small input perturbations may lead to unpredictable behavior.

By Manuel Wendl, Lukas Koller, Tobias Ladner, Matthias Althoff

agents reinforcement-learning benchmarks safety

arXiv AI

Jul 7

Demonstrating Generalization Failures via Mixtures of Conditional Policies

arXiv:2607. 03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments.

By Jou Barzdukas, Jack Peck, Julian Schulz, Paulius Rauba, Steven Basart, Lennie Wells

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 7

Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models

arXiv:2607. 05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows.

By Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin'ichi Satoh, Tanuja Ganu, Rajiv Ratn Shah

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 7

Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models

arXiv:2607. 02869v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models.

By Anagha Radhakrishna Palandye, Rebecca Glick, Osheen Kaul

llms reinforcement-learning fine-tuning

arXiv AI

Jul 7

Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning

arXiv:2506. 05716v2 Announce Type: replace-cross Abstract: Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisation operation over noisy value estimates.

By Adrian Ly, Richard Dazeley, Peter Vamplew, Francisco Cruz, Sunil Aryal

reinforcement-learning benchmarks safety

arXiv AI

Jul 7

Adaptive Margin RLHF via Preference over Preferences

arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.

By Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum

reinforcement-learning safety

arXiv Machine Learning

Jul 7

On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models

arXiv:2607. 04332v1 Announce Type: new Abstract: In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reasoning accuracy and verbalize its confidence.

By Chee Heng Tan, Zhuoyi Lin, Mehul Motani, Wee Sun Lee

llms reinforcement-learning

arXiv AI

Jul 7

SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space

arXiv:2603. 26720v3 Announce Type: replace-cross Abstract: Predicting surgical needle trajectories from endoscopic video is critical for robot-assisted suturing, enabling anticipatory planning, real-time guidance, and safer motion execution.

By Huanrong Liu, Chunlin Tian, Tongyu Jia, Tailai Zhou, Qin Liu, Yu Gao, Yutong Ban, Yun Gu, Guy Rosman, Xin Ma, Qingbiao Li

agents reinforcement-learning robotics

arXiv AI

Jul 7

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

arXiv:2607. 02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge.

By Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu, Zipeng Ye, Defeng Li, Jiayu Shen, Jialing Tao, Hui Xue

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 7

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.

By Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jul 7

A Sliding-Window-Based Reinforcement Learning for Dynamic Assembly Flow Shop Scheduling with Multi-Product Delivery

arXiv:2607. 02941v1 Announce Type: new Abstract: Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arrivals simultaneously alter supply dependencies and the set of feasible job-machine assignments.

By Junhao Qiu, Jianjun Liu, Ting Liu, Rongjie Liao, Zhantao Li, Qingfu Zhang

reinforcement-learning

arXiv AI

Jul 7

Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning

arXiv:2607. 04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models.

By Matthew Foutter, Matteo Cercola, Lena Wild, Yunshan Wang, Michelle Li, Daniele Gammelli, Marco Pavone

agents reinforcement-learning robotics multimodal benchmarks safety

Get the daily briefing