Curriculum RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 61

All topics

EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Jul 7, 2026Mianqiu Huang, Taofeng Xue, Chong Peng +12RL for GUI Agents Partially Observable RL
1Meituan · 2Fudan University · 3Shanghai Jiao Tong University +1
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Jul 5, 2026Yujin Kim, Namgyu Ho, Sangmin Hwang +7RL for Language Models Reinforcement Learning
1KAIST · 2Upstage · University of Toronto +2
Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1
Jun 28, 2026Jesse Ponnock, Lucas HoReinforcement Learning Curriculum RL
Johns Hopkins University
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Jun 23, 2026Yongjin Yang, Jiarui Liu, Yinghui He +3RL for Language Model Reasoning Curriculum RL
Jinesis Lab, University of Toronto & Vector Institute1 · Carnegie Mellon University2 · Princeton University3 +4
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Jun 21, 2026Songtao Tian, Guhan Chen, Bohan Li +2Curriculum RL Few-Step Diffusion Sampling
1Tsinghua University, Beijing, China · 2Huawei Large Model Data Technology Lab, Shenzhen, China
Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model
Jun 21, 2026Pengxiang Cai, Tianchen Fang, Xiaohan Li +3RL for Language Model Reasoning Curriculum RL
The Hong Kong University of Science and Technology (Guangzhou) · Nanyang Technological University · Zhejiang University
Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
Jun 21, 2026Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7Reinforcement Learning RL for Language Model Reasoning
Johns Hopkins University · Rice University · University of Haifa +2
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
Jun 18, 2026Darrien McKenzie, Nicklas Hansen, Xiaolong WangMulti-Armed Bandits RL for Language Model Reasoning
University of California, San Diego
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Jun 16, 2026Byung-Kwan Lee, Ximing Lu, Shizhe Diao +6Curriculum RL LLM-Guided RL
NVIDIA
From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving
Jun 12, 2026Yuewen Mei, Tong Nie, Jie Sun +3Adversarial Training Autonomous Driving
College of Transportation & Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai, 201804, China · Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wild
Jun 10, 2026Sidney Tio, Arunesh Sinha, Pradeep VarakanthamIntelligent Tutoring Systems AI in Education
School of Computing and Information Systems Singapore Management University · Department of Management Science and Information Systems Rutgers Business School
RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
Jun 9, 2026Yichao Zhong, Yidan Lu, Yuhang Lu +9Reinforcement Learning Robot Skill Learning
The University of Hong Kong · Archon Robotics · The Chinese University of Hong Kong
Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
Jun 8, 2026Luca Ghisi, Jacopo Essenziale, Carlo D'Eramo +1Curriculum RL Autonomous Racing
Universit`a degli Studi di Milano · Funny Tales · University of Würzburg
HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
Jun 3, 2026Chenhao Bai, Liqin Lu, Kaijun Wang +5Domain Randomization Curriculum RL
1Zhejiang University, State Key Lab of CAD & CG · 2Zhejiang University of Technology
GUI-C $^2$ : Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
May 29, 2026Junlong Li, Chao Hao, Lap-Pui Chau +1Multimodal Grounding Agentic RL
The Hong Kong Polytechnic University
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
May 26, 2026Zehao Liu, Yuanpu Cao, Jinghui Chen +1Reinforcement Learning On-Policy Self-Distillation
College of Information Sciences and Technology Pennsylvania State University
Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat
May 24, 2026Chengwei Li, Junlin Liu, Yang GaoMulti-Agent Coordination Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
Curriculum reinforcement learning with measurable task representation learning
May 22, 2026Yongyan Wen, Siyuan Li, Mingjian Fu +3Representation Learning Curriculum RL
Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China · Fuzhou University, Fuzhou, 350108, Fujian, China · China Academy of Sciences, Beijing, 100190, China +1
What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA
May 21, 2026Xinjie He, Zhiyuan Lin, Su Liu +4Memory-Augmented Neural Networks Curriculum RL
Columbia University · Independent Researcher · Johns Hopkins University +1
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
May 21, 2026Xitai Jiang, Zihan Tang, Wenze Lin +3RL for Language Model Reasoning Credit Assignment in RL
LeapLab, Tsinghua University · Qiuzhen College, Tsinghua University · B Gao Huang
Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
May 18, 2026Baoteng Li, Xianghao Zang, Xinran Wang +8Group Relative Policy Optimization Curriculum RL
School of Artificial Intelligence, Beijing University of Posts and Telecommunications1 · Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance3 · Institute of Artificial Intelligence (TeleAI), China Telecom2
D $^2$ Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
May 16, 2026Ru Zhang, Renda Li, Ziyu Ma +4RL for Language Model Reasoning Curriculum RL
Alibaba Group · AMAP, Alibaba Group · BUPT
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
May 12, 2026Jianghan Shen, Siqi Luo, Xinyu Cheng +6RL for Language Models Reinforcement Learning
1Nanjing University · 2Shanghai Artificial Intelligence Laboratory · University of Hong Kong +1
fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum
May 12, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Reinforcement Learning RL for Language Model Reasoning
OPPO AI Center
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
May 11, 2026Han Zheng, Yining Ma, Karthick Gunasekaran +4Reinforcement Learning Meta-Learning
MIT · Amazon AGI
expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling
May 11, 2026Mingxiong Lin, Zhangquan Gong, Maowen Tang +6Reinforcement Learning KL-Regularized RL
OPPO AI Center
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
May 7, 2026Yujia Chen, Yang Ye, Xiao Chu +2RL for Code Generation Reinforcement Learning
Harbin Institute of Technology, Shenzhen · Huawei Cloud Computing Technologies Co., Ltd.
Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards
May 3, 2026Rudray Dave, Vedang Dubey, Smit Deoghare +1Reinforcement Learning RL for Language Model Reasoning
Department of Artificial Intelligence Sardar Vallabhbhai National Institute of Technology Surat, India
Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum
Mar 5, 2026Shan Ning, Longtian Qiu, Xuming HeVisual Question Answering Reinforcement Learning
ShanghaiTech University, Shanghai, China · Lingang Laboratory, Shanghai, China · Shanghai Engineering Research Center of Intelligent Vision and Imaging
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Jan 26, 2026Shobhita Sundaram, John Quan, Ariel Kwiatkowski +3Self-Play RL RL for Language Model Reasoning
1MIT · 2Meta FAIR · 3New York University

Jul 7, 2026, cs.AIJ/K move · Enter open · S save

EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents

Mianqiu Huang, Taofeng Xue, Chong Peng, Jinrui Ding+11

1Meituan · 2Fudan University · 3Shanghai Jiao Tong University+1

RL for GUI Agents Partially Observable RL Computer-Use Agents Curriculum RL RL for LLM Agents

Open paper AskPDF arXiv

Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover the causal feedback loop of real computer use: each action changes the screen state, future action space, and recovery options. EvoCUA-1.5 extends self-evolving computer-use agents from offline experience learning to online reinforcement learning, where policies interact with executable sandbox environments and improve from verifiable task outcomes. Online RL in this setting requires more than directly reusing single-turn language-RL recipes. Multi-turn interaction introduces context-managed observations, sparse terminal rewards, variable-length trajectories, and slow environment feedback. EvoCUA-1.5 addresses these challenges with Step-Level Policy Optimization (STEPO), which preserves trajectory-level advantage balance after decomposition into step-level samples; policy-aware filtering and pass-rate calibration over verifiable synthesized tasks; Dynamic Tri-Adaptive Curriculum (DTAC), which combines learnable tasks, difficult positive replay, and controlled infeasible-task exposure; and a fully asynchronous RL infrastructure with staleness control and mini-group batching. Experiments show that these components improve training stability and downstream performance. EvoCUA-1.5 achieves 63.2% success on OSWorld-Verified, outperforming comparable 32B/35B-scale open-weight baselines and even approaching models with significantly larger parameter counts. Overall, EvoCUA-1.5 provides a practical framework for scaling online RL in multi-turn computer-use agents.

Momentum

Related topics

Latest papers 61