Reinforcement learning

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

7,056 stories · RSS feed

arXiv Machine Learning

Jul 17

Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows

arXiv:2607. 14272v1 Announce Type: new Abstract: Flow matching has emerged as an effective framework for learning complex data distributions, but adapting pretrained flow models to new tasks often requires computationally expensive retraining.

By Jingdong Zhang, Xinze Li, Yize Jiang, Luan Yang, Minkai Xu, Junhong Liu

diffusion reinforcement-learning benchmarks

arXiv AI

Jul 17

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

arXiv:2607. 14682v1 Announce Type: new Abstract: Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge.

By Harikrishnan P M, Goutham Vignesh, Ganesh Parab, Saisubramaniam Gopalakrishnan, Vishal Vaddina, Varun V, Rohit Agrawal

nlp reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 17

Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities

arXiv:2408. 12548v3 Announce Type: replace Abstract: Machine Learning (ML) has become central to Autonomous Vehicles (AVs), supporting perception, prediction, planning, control, and decision-making in dynamic environments.

By Yousef Emami, Mohammadhossein Homaei, Miguel Guti\'errez Gait\'an, Luis Almeida, Kai Li, Hui Huang, Zhu Han

llms agents computer-vision reinforcement-learning safety

arXiv Machine Learning

Jul 17

SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems

arXiv:2506. 02255v2 Announce Type: replace Abstract: Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints, mixed-integer decisions, and industrial complexity.

By Asha Ramanujam (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Adam Elyoumi (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Hao Chen (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Sai Madhukiran Kompalli (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Akshdeep Singh Ahluwalia (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Shraman Pal (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN), Dimitri J. Papageorgiou (Energy Sciences, ExxonMobil Technology and Engineering Company, Annandale, NJ), Can Li (Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN)

reinforcement-learning robotics benchmarks

arXiv AI

Jul 17

Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation

arXiv:2607. 14962v1 Announce Type: cross Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes.

By Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, Yutaka Matsuo

diffusion reinforcement-learning safety

arXiv Machine Learning

Jul 17

On-Policy Delta Distillation

arXiv:2607. 15161v1 Announce Type: new Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model.

By Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 17

Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning

arXiv:2506. 12529v2 Announce Type: replace-cross Abstract: Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering.

By Sara Rajaram, R. James Cotton, Fabian H. Sinz

reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 17

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

arXiv:2607. 14952v1 Announce Type: new Abstract: A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment.

By Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao, Harry Zhang, Irvine Lu, Nolan Ho, Lucian Li, Andrew Lei, Cleon Cheng, Steven Chiang, Yihang Zeng, Di Zhang, Rio Yang, Kaijie Chen, Andrew Chen, Pony Ma, Weizhong Zhang, Cheng Jin

agents reinforcement-learning

arXiv AI

Jul 17

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

arXiv:2607. 14614v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping.

By Weiwen Xu, Jia Liu, Hou Pong Chan, Long Li, Deng Cai, Min Chen, Hao Zhang

reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jul 17

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

arXiv:2310. 07211v2 Announce Type: replace Abstract: Regularization is a cornerstone of modern reinforcement learning.

By Zeyang Li, Chuxiong Hu, Yunan Wang, Guojian Zhan, Jie Li, Yao Lyu, Shengbo Eben Li

reinforcement-learning

arXiv AI

Jul 17

Fast-Fading Channel and Power Optimization of the Magnetic Inductive Cellular Network

arXiv:2406. 04737v2 Announce Type: cross Abstract: The cellular network of magnetic Induction (MI) communication holds promise in long-distance underground environments.

By Honglei Ma, Erwu Liu, Zhijun Fang, Rui Wang, Yongbin Gao, Wenjun Yu, Dongming Zhang

reinforcement-learning efficiency

arXiv AI

Jul 17

Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation

arXiv:2605. 25170v2 Announce Type: replace-cross Abstract: Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models.

By Kordel K. France, Ovidiu Daescu

llms agents computer-vision reinforcement-learning robotics efficiency

arXiv Machine Learning

Jul 17

Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization

arXiv:2605. 21751v2 Announce Type: replace Abstract: Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data.

By Zhiqi Gao, Albert Ge, Alexander Berenbeim, Nathaniel D. Bastian, Frederic Sala

reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 17

Intelligent Three Level Learning Architecture for Autonomous UAV Swarms in Search and Rescue

arXiv:2607. 14093v1 Announce Type: new Abstract: This paper presents a novel three level hierarchical learning architecture for autonomous UAV swarms performing search and rescue operations.

By Oleksii Bychkov

agents reinforcement-learning safety

arXiv AI

Jul 17

Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis

arXiv:2503. 18607v2 Announce Type: replace-cross Abstract: We introduce the Switching Non-Stationary Markov Decision Process (SNS-MDP) framework, in which the environment transitions among a finite set of MDPs governed by a latent Markov chain while the agent observes only the external state.

By Mohsen Amiri, Sindri Magn\'usson

agents reinforcement-learning

arXiv AI

Jul 17

An offline approach to fNIRS-guided reinforcement learning for robot behavior

arXiv:2607. 14393v1 Announce Type: cross Abstract: Human-in-the-loop Reinforcement Learning has become a popular approach to training, finetuning, and aligning robot behavior with user preferences.

By Julia Santaniello, Madelaine Brower, Benson Jiang, Donatello Sassaroli, Robert Jacob, Jivko Sinapov

agents reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Jul 17

Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning

arXiv:2607. 14171v1 Announce Type: new Abstract: Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes.

By Bowei He, Yankai Chen, Xiaokun Zhang, Xue Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 17

Mask-Aware Policy Gradients for Diffusion Language Models

arXiv:2607. 15200v1 Announce Type: cross Abstract: Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation.

By Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Kr\"ahenb\"uhl

llms diffusion reinforcement-learning benchmarks

arXiv AI

Jul 17

Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents

arXiv:2607. 15095v1 Announce Type: cross Abstract: The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions.

By Dylan Van Mulders, Matthias Bogaert, Dirk Van den Poel

llms rag agents reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 17

Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation

arXiv:2607. 14895v1 Announce Type: new Abstract: Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding.

By Yu-Du Feng, Niels M\"undler-Sasahara, Mark Vero, Martin Vechev

llms nlp reinforcement-learning fine-tuning

Get the daily briefing