Image de couverture de livre

From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zezhou, Zhang, Ziyun, Zhang, Xiaoyi, Qian, Zhuzhong, Lu, Yan
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
par: Zhang, Ziyun, et autres
Publié: (2026)

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
par: Zhang, Wenhao, et autres
Publié: (2025)

Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
par: Meng, Wenjia, et autres
Publié: (2024)

Soft Policy Optimization: Online Off-Policy RL for Sequence Models
par: Cohen, Taco, et autres
Publié: (2025)

InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
par: Liu, Yuhang, et autres
Publié: (2025)

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
par: Xi, Zhiheng, et autres
Publié: (2025)

Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback
par: Xiao, Teng, et autres
Publié: (2024)

Learning to Reason under Off-Policy Guidance
par: Yan, Jianhao, et autres
Publié: (2025)

Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
par: Jiang, Jie, et autres
Publié: (2026)

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles
par: Yan, Lu, et autres
Publié: (2026)

Maximum Entropy Reinforcement Learning with Diffusion Policy
par: Dong, Xiaoyi, et autres
Publié: (2025)

EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
par: Song, Siyao, et autres
Publié: (2025)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
par: Liu, Zeyuan, et autres
Publié: (2026)

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
par: Zhang, Yan, et autres
Publié: (2026)

Style-Preserving Policy Optimization for Game Agents
par: Li, Lingfeng, et autres
Publié: (2025)

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
par: Zhao, Shiwan, et autres
Publié: (2026)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
par: Lobo, Elita, et autres
Publié: (2024)

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
par: Deng, Zhirui, et autres
Publié: (2024)

Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound
par: Fiskus, Tal, et autres
Publié: (2025)

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals
par: Wei, Xing, et autres
Publié: (2025)

Zero-Shot Off-Policy Learning
par: Asadulaev, Arip, et autres
Publié: (2026)

Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
par: Jiao, Zhengbo, et autres
Publié: (2026)

Clustering Context in Off-Policy Evaluation
par: Guzman-Olivares, Daniel, et autres
Publié: (2025)

Concept-driven Off Policy Evaluation
par: Majumdar, Ritam, et autres
Publié: (2024)

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
par: Fakoor, Rasool, et autres
Publié: (2026)

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
par: Lee, Haanvid, et autres
Publié: (2024)

Off-Policy Correction For Multi-Agent Reinforcement Learning
par: Zawalski, Michał, et autres
Publié: (2021)

Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles
par: Zhang, Ruoqi, et autres
Publié: (2025)

Reinforcing Language Agents via Policy Optimization with Action Decomposition
par: Wen, Muning, et autres
Publié: (2024)

Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
par: Ren, Yanwei, et autres
Publié: (2026)

Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs
par: Zhang, Yuheng, et autres
Publié: (2025)

Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
par: Wang, Yibo, et autres
Publié: (2026)

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
par: Ye, Chenlu, et autres
Publié: (2026)

Automated Off-Policy Estimator Selection via Supervised Learning
par: Felicioni, Nicolò, et autres
Publié: (2024)

D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss
par: Zou, Guowei, et autres
Publié: (2025)

Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation
par: Zhai, Shaopeng, et autres
Publié: (2023)

Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
par: Huang, Luke J., et autres
Publié: (2026)

Selective Off-Policy Reference Tuning with Plan Guidance
par: Le, Duc Anh, et autres
Publié: (2026)

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
par: Zhang, Wenqi, et autres
Publié: (2024)

Graph-Enhanced Policy Optimization in LLM Agent Training
par: Yuan, Jiazhen, et autres
Publié: (2025)