Reinforcement learning

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

7,243 stories · RSS feed

arXiv AI

Jun 3

Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles

arXiv:2505. 08222v3 Announce Type: replace-cross Abstract: Autonomous vehicles (AVs) offer a cost-effective solution for scientific missions such as underwater tracking.

By Matteo Gallici, Ivan Masmitja, Mario Mart\'in

llms agents reinforcement-learning robotics

arXiv Machine Learning

Jun 3

Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning

arXiv:2606. 03361v1 Announce Type: new Abstract: Rubric-based rewards are increasingly used for open-ended language model post-training, but criterion-level scores are often aggregated as independent utilities.

By Can Lv, Mingju Chen, Heng Chang, Shiji Zhou

llms reinforcement-learning

arXiv Machine Learning

Jun 3

Coherent Swap Regret and Channel-Proof Learning

arXiv:2606. 02655v1 Announce Type: cross Abstract: External regret certifies stability only against replacing one's behavior by a fixed alternative.

By Sohail Sarkar

reinforcement-learning benchmarks

arXiv AI

Jun 3

Aletheia: What Makes RLVR For Code Verifiers Tick?

arXiv:2601. 12186v3 Announce Type: replace-cross Abstract: Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training.

By Vatsal Venkatkrishna, Indraneil Paul, Iryna Gurevych

reinforcement-learning

arXiv Machine Learning

Jun 3

LC-SAC: Lyapunov-Constrained Soft Actor-Critic via Koopman Operator Theory for Trajectory Tracking and Stabilization

arXiv:2602. 04132v4 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has achieved remarkable success in solving complex sequential decision-making problems.

By Dhruv S. Kushwaha, Zoleikha A. Biron

reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 3

Learning Unmasking Policies for Diffusion Language Models

arXiv:2512. 09106v4 Announce Type: replace Abstract: Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference.

By Metod Jazbec, Theo X. Olausson, Louis B\'ethune, Pierre Ablin, Michael Kirchhof, Jo\~ao Monteiro, Victor Turrisi, Jason Ramapuram, Marco Cuturi

llms diffusion reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jun 3

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion

arXiv:2606. 03441v1 Announce Type: cross Abstract: Autonomous vision-based perching of quadrotors on moving inclined platforms is critical for air-ground collaboration but remains challenging due to the limited field of view (FOV).

By Zihong Lu, Zongzhuo Liu, Huaxu Li, Jinqiang Cui, Jie Mei, Youmin Gong, U Kei Cheang, Boyu Zhou

agents reinforcement-learning fine-tuning

arXiv AI

Jun 3

Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin

arXiv:2606. 02614v1 Announce Type: cross Abstract: The Brazilian Equatorial Margin (BEM) is Brazil's next offshore oil frontier, with operations expected to begin in 2026 in the Foz do Amazonas basin.

By Antonio de Sousa Leit\~ao Filho, Fabr\'icio Saul Lima, Selby Mykael Lima dos Santos, Rejani Bandeira Vieira Sousa, Lu\'is Jorge Mesquita de Jesus, Dennys Correia da Silva, Allan Kardec Duailibe Barros Filho

agents reinforcement-learning

arXiv Machine Learning

Jun 3

Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Review

arXiv:2606. 02902v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) is increasingly applied to de novo molecular design, but choices in data, rewards, and evaluation can yield uneven performance across disease areas and chemotypes.

By Esmaeil Shakeri, Ronnie de Souza Santos, Behrouz Far

reinforcement-learning safety

arXiv AI

Jun 3

Efficient Hyperparameter Optimization for LLM Reinforcement Learning

arXiv:2606. 03073v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter configurations, making hyperparameter optimization (HPO) essential yet computationally expensive.

By Minping Chen, Bowen Xiao, Du Liang, Chuxuan Zeng, Zeyi Wen

llms reinforcement-learning

arXiv AI

Jun 3

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

arXiv:2606. 03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static.

By Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye

llms agents reinforcement-learning

arXiv AI

Jun 3

The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models

arXiv:2606. 03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.

By Liuyuan Wen, Xun Zhu, Lihao Huang, Wenbin Li, Yang Gao

llms reinforcement-learning efficiency safety

arXiv Machine Learning

Jun 3

Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

arXiv:2510. 08977v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data.

By Chuyi Tan, Peiwen Yuan, Xinglin Wang, Yiwei Li, Shaoxiong Feng, Yueqi Zhang, Jiayi Shi, Ji Zhang, Boyuan Pan, Yao Hu, Kan Li

llms reinforcement-learning safety

arXiv Machine Learning

Jun 3

Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments

arXiv:2606. 03698v1 Announce Type: new Abstract: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynamic environments.

By Sangeun Park, Minhae Kwon

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 3

Easy-to-Use Shielding for Reinforcement Learning

arXiv:2606. 03804v1 Announce Type: new Abstract: Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment.

By Stefan Pranger, Bettina K\"onighofer

agents reinforcement-learning safety

arXiv AI

Jun 3

AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following

arXiv:2606. 03116v1 Announce Type: cross Abstract: The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation.

By Haitao Li, Tian Tan, Yuguang Yang, Shan Yang, Xie Chen

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 3

Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning

arXiv:2606. 03118v1 Announce Type: new Abstract: Objective: Diseases such as age-related macular degeneration and retinitis pigmentosa cause the degradation of the photoreceptor layer.

By Jacob Lavoie, Marwan Besrour, William Lemaire, Jean Rouat, R\'ejean Fontaine, Eric Plourde

agents reinforcement-learning

arXiv AI

Jun 3

Reinforcement Learning from Cross-domain Videos with Video Prediction Model

arXiv:2606. 03201v1 Announce Type: cross Abstract: Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of domain gaps.

By Zhao Yang, Xinrui Zu, Jacob E. Kooi, Thomas Delliaux, He Liu, Shujian Yu, Kevin Sebastian Luck, Vincent Fran\c{c}ois-Lavet

agents reinforcement-learning robotics

arXiv AI

Jun 3

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

arXiv:2606. 03382v1 Announce Type: cross Abstract: While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments.

By Bingxu Liu, Jiashun Liu, Johan Obando-Ceron, Hao Wang, Runze Liu, Pablo Samuel Castro, Aaron Courville, Ling Pan

llms reinforcement-learning robotics

arXiv AI

Jun 3

Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection

arXiv:2606. 03937v1 Announce Type: new Abstract: While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether this mechanism still holds in visual reasoning.

By Senjie Jin, Peixin Wang, Boyang Liu, Xiaoran Fan, Shuo Li, Zhiheng Xi, Jiazheng Zhang, Yuhao Zhou, Tao Gui, Qi Zhang, Xuanjing Huang

reinforcement-learning multimodal

Get the daily briefing