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 2

Mean-Field Diffuser: Scaling Offline MARL to Thousands of Agents

arXiv:2605. 30190v2 Announce Type: replace Abstract: Diffusion-based planning has achieved strong results in single-agent offline reinforcement learning, yet scaling to many-agent systems remains intractable due to the curse of dimensionality in the joint trajectory space.

By Wenhao Li, Xiangfeng Wang, Bo Jin

agents diffusion reinforcement-learning benchmarks safety

arXiv AI

Jun 2

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

arXiv:2606. 01286v1 Announce Type: cross Abstract: The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal.

By Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao, Ziheng Zhou, Mert Cemri, Shu Liu, Yuran Xiu, Chenxiao Yan, Haikun Zhao, Bin Yu, Ion Stoica, Dawn Song

llms reinforcement-learning benchmarks

arXiv AI

Jun 2

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).

By Yixiu Mao, Yun Qu, Qi Wang, Heming Zou, Xiangyang Ji

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 2

World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications

arXiv:2606. 00133v1 Announce Type: new Abstract: World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artificial general intelligence, enabling agents to predict, plan, and reason within learned representations.

By Arif Hassan Zidan, Yi Pan, Hanqi Jiang, Ruiyu Yan, Wei Ruan, Zihao Wu, Lifeng Chen, Weihang You, Xinliang Li, Bowen Chen, Huawen Hu, Peilong Wang, Sizhuang Liu, Jing Zhang, Siyuan Li, Zhengliang Liu, Yu Bao, Lin Zhao, Lichao Sun, Dajiang Zhu, Xiang Li, Jinglei Lv, Quanzheng Li, Wei Liu, Tianming Liu, Wei Zhang

llms agents diffusion reinforcement-learning robotics multimodal benchmarks safety

arXiv AI

Jun 2

Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling

arXiv:2606. 01220v1 Announce Type: cross Abstract: Generating molecules that simultaneously satisfy drug-like properties and conform to the 3D structure of a target protein is a core challenge in structure-based drug design (SBDD).

By Guang Lin, Shikui Tu, Lei Xu

diffusion reinforcement-learning fine-tuning benchmarks data-engineering

arXiv AI

Jun 2

MiCU: End-to-End Smart Home Command Understanding with Large Language Model

arXiv:2606. 01099v1 Announce Type: cross Abstract: Command understanding systems in smart home ecosystems can automate device control and substantially improve user experience.

By Haowei Han, Kexin Hu, Weiwei Cai, Debiao Zhang, Bin Qin, Yuxiang Wang, Jiawei Jiang, Xiao Yan, Bo Du

llms reinforcement-learning

arXiv AI

Jun 2

Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing

arXiv:2606. 02218v1 Announce Type: cross Abstract: Synchronous reinforcement learning methods such as Group Relative Policy Optimization (GRPO) provide stable and reproducible on-policy training, but they are highly vulnerable to stragglers, a single unusually long rollout can delay reward computation and parameter updates for the entire group.

By Azal Ahmad Khan, Ammar Ahmed, Zeshan Fayyaz, Sheng Di, Mingyi Hong, Ali Anwar

reinforcement-learning benchmarks

arXiv AI

Jun 2

Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reduction

arXiv:2606. 00949v1 Announce Type: cross Abstract: We propose a method combining Multi-Agent Deep Reinforcement Learning (MARL) and eXplainable Deep Learning (XDL) to reduce drag in wall-bounded turbulent flows.

By Federica Tonti, Ricardo Vinuesa

agents reinforcement-learning

arXiv AI

Jun 2

Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts

arXiv:2606. 01162v1 Announce Type: new Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources.

By Ya Shen, Gang Chen, Hui Ma, Mengjie Zhang

reinforcement-learning benchmarks

arXiv AI

Jun 2

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

arXiv:2606. 01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths.

By Atoosa Chegini, Soheil Feizi

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 2

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs

arXiv:2606. 00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reasoning capabilities on out-of-distribution (OOD) tasks.

By Zihan Chen, Yiming Zhang, Wenxiang Geng, Zenghui Ding, Yining Sun

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 2

Interpretable Policy Distillation for Power Grid Topology Control

arXiv:2606. 00561v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to deploy on constrained hardware, and opaque to operators.

By Aleksandra Dmitruka, Karlis Freivalds

agents reinforcement-learning efficiency

arXiv Machine Learning

Jun 2

NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming

arXiv:2602. 17737v2 Announce Type: replace-cross Abstract: Mutual adaptation is a central challenge in human-AI teaming, as humans naturally adjust their strategies in response to an AI agent's behavior.

By Upasana Biswas, Durgesh Kalwar, Subbarao Kambhampati, Sarath Sreedharan

agents reinforcement-learning benchmarks

arXiv AI

Jun 2

Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning

arXiv:2606. 00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely attributed to the advent of Large Language Models and their misalignment with natural language usage.

By Xiaoyang Ming, Jose Hernandez, Thomas Stephan Juzek

llms reinforcement-learning safety

arXiv AI

Jun 2

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.

By Hongqiang Lin, Pengfei Wang, Nenggan Zheng

reinforcement-learning benchmarks

arXiv AI

Jun 2

ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate

arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.

By Rodney Lafuente-Mercado

llms reinforcement-learning fine-tuning

arXiv AI

Jun 2

Agentic Transformers Provably Learn to Search via Reinforcement Learning

arXiv:2606. 00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives.

By Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi

llms agents reinforcement-learning

arXiv AI

Jun 2

TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control

arXiv:2604. 17456v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown strong capabilities in long-horizon reasoning, tool use, and decision-making in digital environments, yet extending them to physically grounded systems remains challenging.

By Siqi Lai, Pan Zhang, Yuping Zhou, Jindong Han, Yansong Ning, Hao Liu

llms agents reinforcement-learning

arXiv AI

Jun 2

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

arXiv:2606. 02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites.

By Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

Jun 2

SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant

arXiv:2606. 00015v1 Announce Type: cross Abstract: Operating Systems (OS) courses are among the most challenging in computer science education due to the complexity of internal structures and the diversity of running environments.

By Yifan Zhang, Xinkui Zhao, Zuxin Wang, Zhengyi Zhou, Guanjie Chen, Shuiguang Deng, Jianwei Yin

llms rag agents reinforcement-learning

Get the daily briefing