Reinforcement learning

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

6,685 stories · RSS feed

arXiv Computation and Language

Oct 15

ProReviewer: Evidence-Driven Investigation for Scientific Peer Review

arXiv:2606.13349v2 Announce Type: replace Abstract: Effective peer review requires adaptive investigation that responds to evidence emerging from each paper. Existing LLM-based reviewers largely orga...

By Haishuo Fang, Yue Feng, Iryna Gurevych

llms agents reinforcement-learning

arXiv AI

Oct 15

Reinforcement Learning In Partially Verifiable Environments for Colon Cancer Treatment Planning

arXiv:2610.17426v1 Announce Type: cross Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often wi...

By Li-Ching Chen, Andr\'es Franco Valiente, Yuta Ishiyama, Zachary R. Chalmers, William Chen, Kelsey Natsuhara, Taema Brinjikji, Madhumita Sushil, Travis Zack, Julian C. Hong

llms agents reinforcement-learning safety

arXiv Machine Learning

Oct 15

Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments

arXiv:2610.19104v1 Announce Type: cross Abstract: Learning an individualized treatment rule (ITR) with many treatments requires estimating treatment-specific effects from limited observations per arm...

By Daixi Huang, Yixin Yuan, Yifan Dai, Yufeng Liu

rag reinforcement-learning

arXiv AI

Oct 15

Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning

arXiv:2610.15681v1 Announce Type: cross Abstract: Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design...

By Qingwang Zhang, Jiahao Li, Xiangdong Zhou

reinforcement-learning safety

arXiv AI

Oct 15

Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning

arXiv:2610.17734v1 Announce Type: cross Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent s...

By Yutong Chen, Zhichao Xu, Rui Liu, Kunpeng Liu

llms reinforcement-learning efficiency benchmarks

arXiv AI

Oct 15

Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation

arXiv:2610.16593v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) implemented with Group Relative Policy Optimization (GRPO) has driven substantial progress in tra...

By Haifeng Qian, David Mosallanezhad, Christian Munley, Adithya Renduchintala, Oleksii Kuchaiev

llms reinforcement-learning

arXiv AI

Oct 15

VLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models

arXiv:2610.16567v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) have achieved high success rates on familiar manipulation tasks, yet it remains unclear whether such scores refl...

By Jun Xiao, Rui Ye, Dong Cao, Jinyu Gu, Ying Wang, Zhiliang Zhu

reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Oct 15

Few-for-Many Best-Arm Identification in Multi-Objective Bandits

arXiv:2610.16840v1 Announce Type: cross Abstract: Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling eac...

By Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin, Shuang Qiu

reinforcement-learning

arXiv AI

Oct 15

PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning

arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers wit...

By Changguo Jia, Zhiyou Xiao, Xinbei Ma, Geng Chen, Weiming Zhang, Yiming Xu, Tianqi Zhao, Minghui Zhou

reinforcement-learning benchmarks

arXiv AI

Oct 15

From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning

arXiv:2610.16984v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn effective policies from fixed datasets without environment interaction. Although generative models such...

By Shenghua Lu, Zixuan Yang, Rongxu Zhao, Bohao Qu, Jifeng Hu, Hechang Chen

diffusion reinforcement-learning benchmarks

arXiv AI

Oct 15

Certifying Almost-Sure Reachability in Unknown MDPs

arXiv:2610.18119v1 Announce Type: cross Abstract: {\em Specification-Guided Reinforcement Learning (RL)} has largely concerned itself with \emph{learning} an optimal policy against a formal specifica...

By S Akshay, Suguman Bansal, Gaurav Mahla

reinforcement-learning safety

arXiv AI

Oct 15

Unlocking Token Rewards via Training-Free Reward Attribution

arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward mode...

By Sitong Wu, Haoru Tan, Bin Xia, Xichen Zhang, Jingyao Li, Shaofeng Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia

llms rag reinforcement-learning benchmarks

arXiv Machine Learning

Oct 15

Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter

arXiv:2610.20041v1 Announce Type: new Abstract: A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converte...

By Samuela Rokocakau, Panagiotis Kakosimos, Giulia Tresca, Pericle Zanchetta

reinforcement-learning

arXiv Machine Learning

Oct 15

Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL

arXiv:2610.20009v1 Announce Type: new Abstract: Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching per...

By Timo Klein, Thomas Lang, Andrii Shkabrii, Lukas Miklautz, Yllka Velaj, Sebastian Tschiatschek

agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Oct 15

Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction

arXiv:2610.19883v1 Announce Type: new Abstract: The growing interest in behavior foundation models, combined with recent advancements in generative modeling, has led to an appealing recipe for reinfo...

By Robin Uhrich, Marco Bagatella, N\'uria Armengol Urp\'i, Pavel Kolev, Georg Martius

reinforcement-learning efficiency multimodal benchmarks

arXiv Machine Learning

Oct 15

On the Convergence of Semi-Gradient TD: A Mean Field Perspective

arXiv:2610.20014v1 Announce Type: new Abstract: Semi-gradient temporal-difference learning is a core algorithmic component of reinforcement learning, but bootstrapping with function approximation gen...

By Haruki Settai, Tadashi Kozuno, Shinji Ito

reinforcement-learning safety

arXiv AI

Oct 15

ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition

arXiv:2601.03822v2 Announce Type: replace Abstract: Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computa...

By Muyang Zhao, Chunhao Tian, Qi Qi, Hao Sun

llms nlp reinforcement-learning fine-tuning

arXiv AI

Oct 15

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

arXiv:2610.14448v1 Announce Type: cross Abstract: Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail...

By Sihwan Park, Sung-Yub Kim, Doohyuk Jang, Eunho Yang

reinforcement-learning efficiency benchmarks

arXiv AI

Oct 15

SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise

arXiv:2610.17093v1 Announce Type: new Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. O...

By Xupeng Chen, Chenqian Le, Jiayi Cheng, Runhao Li, Michael Yue

llms reinforcement-learning fine-tuning safety

arXiv AI

Oct 15

Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, an...

By Petr Senatorov, Karim Vafin, Elena Tutubalina, Oleg Somov

llms reinforcement-learning benchmarks

Get the daily briefing