Reinforcement learning

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

7,243 stories · RSS feed

arXiv Machine Learning

Jun 4

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

arXiv:2606. 04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT).

By Rachit Bansal, Clara Mohri, Tian Qin, David Alvarez-Melis, Sham Kakade

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 4

Explainably Safe Reinforcement Learning

arXiv:2606. 04634v1 Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior.

By Sabine Rieder, Stefan Pranger, Debraj Chakraborty, Jan K\v{r}et\'insk\'y, Bettina K\"onighofer

reinforcement-learning safety

arXiv Machine Learning

Jun 4

MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

arXiv:2606. 04847v1 Announce Type: cross Abstract: Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code.

By Kun Cheng, Songshuo Lu, Sicong Liao, Tankun Li, Yafei Zhang, Dong Yang, Qiheng Lv, Hua Wang, Zhi Chen, Yaohua Tang

llms reinforcement-learning fine-tuning

arXiv AI

Jun 4

Dual Advantage Fields

arXiv:2606. 04188v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons.

By Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin, Dmitry V. Dylov, Fakhri Karray, Vladislav Kurenkov, Martin Tak\'a\v{c}, Arip Asadulaev

rag reinforcement-learning robotics safety

arXiv AI

Jun 4

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

arXiv:2606. 04923v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards.

By Xuekang Wang, Zhuoyuan Hao, Shuo Hou, Hao Peng, Juanzi Li, Xiaozhi Wang

llms agents reinforcement-learning

arXiv AI

Jun 4

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models

arXiv:2606. 04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs.

By Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu, Minhui Xue, Yue Zhao, Chaowei Xiao

llms diffusion reinforcement-learning benchmarks safety

arXiv AI

Jun 4

Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation

arXiv:2606. 04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is context agnostic and may raise two issues: over disclosing untyped sensitive context and over removing answer bearing spans.

By Xinyue Huang, Xiaochun Cao, Wenyuan Yang

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 4

Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents

arXiv:2510. 13704v2 Announce Type: replace-cross Abstract: Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance.

By Johan Obando-Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron Courville, Pablo Samuel Castro

rag agents reinforcement-learning safety

arXiv Machine Learning

Jun 4

Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning

arXiv:2601. 07408v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks.

By Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

Rollout-Level Advantage-Prioritized Experience Replay for GRPO

arXiv:2606. 04560v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards with GRPO is a standard approach for post-training reasoning LLMs.

By Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang, Ik-hwan Kim, Sungroh Yoon

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning

arXiv:2606. 04167v1 Announce Type: cross Abstract: We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro systems to satisfy travel demand.

By Dimitris Michailidis, Sennay Ghebreab, Fernando P. Santos

reinforcement-learning safety

arXiv AI

Jun 4

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

arXiv:2606. 04284v1 Announce Type: cross Abstract: Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values.

By Yifan Wang, Jinyi Mu, Mayank Jobanputra, Yu Wang, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg

llms reinforcement-learning safety

arXiv AI

Jun 4

Vectorized Online POMDP Planning

arXiv:2510. 27191v5 Announce Type: replace-cross Abstract: Planning under partial observability is an essential capability of autonomous robots.

By Marcus Hoerger, Muhammad Sudrajat, Hanna Kurniawati

agents reinforcement-learning robotics benchmarks

arXiv AI

Jun 4

Reinforcement Learning from Rich Feedback with Distributional DAgger

arXiv:2606. 05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct.

By Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad

reinforcement-learning efficiency

arXiv AI

Jun 4

Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers

arXiv:2606. 04328v1 Announce Type: cross Abstract: Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conventional rule-based and optimization-driven radio resource management (RRM) toward artificial intelligence (AI)-driven RRM.

By Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci

llms agents reinforcement-learning fine-tuning

arXiv AI

Jun 4

Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning

arXiv:2605. 28829v2 Announce Type: replace-cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics.

By Ritvik Rastogi, Vishal Singh, Tejas Chaudhari, Sandeep Varma

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 4

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.

By Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su, Hongru Hou, Hengrui Chen, Ao Xu, Deqing Yang

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety

arXiv:2606. 04051v1 Announce Type: cross Abstract: The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation.

By Xian Qi Loye, Qinglin Su, Zhexin Zhang, Shiyao Cui, Qi Zhu, Fei Mi, Hongning Wang, Minlie Huang

llms agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 4

VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation

arXiv:2606. 04632v1 Announce Type: new Abstract: Mechanical ventilation for Acute Respiratory Distress Syndrome (ARDS) requires balancing competing physiological goals, including oxygenation, lung protection, and acid-base homeostasis.

By Teqi Hao, Yuxuan Fu, Xiaoyu Tan, Shaojie Shi, Bohao Lv, Yinghui Xu, Xihe Qiu

llms agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 4

Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning

arXiv:2606. 04574v1 Announce Type: new Abstract: This study aims to determine whether the application of Deep Reinforcement Learning (DRL) as a specialized execution overlay can enhance pair trading in highly volatile cryptocurrency markets.

By Damian Lebied\'z, Robert \'Slepaczuk

agents reinforcement-learning

Get the daily briefing