paper-with-me

Papers

Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions

2026-04-08 · Guo Gan, Yuxuan Ding, Cong Chen, Yuwei Ren, Yin Huang, Hong Zhou arxiv

Online reinforcement learning (RL) serves as an effective method for enhancing the capabilities of Android agents. However, guiding agents to learn through online interaction is prohibitively expensive due to the high latency of emulators and the sample inefficiency of existing RL algorithms. We identify a fundamental limitation in current approaches: the Single State Single Action paradigm, which updates the policy with one-to-one state-action pairs from online one-way rollouts without fully exploring each costly emulator state. In this paper, we propose Android Coach, a novel framework that shifts the training paradigm to Single State Multiple Actions, allowing the agent to sample and utilize multiple actions for a single online state. We enable this without additional emulator overhead by learning a critic that estimates action values. To ensure the critic serves as a reliable coach, we integrate a process reward model and introduce a group-wise advantage estimator based on the averaged critic outputs. Extensive experiments demonstrate the effectiveness and efficiency of Android Coach: it achieves 7.5% and 8.3% success rate improvements on AndroidLab and AndroidWorld over UI-TARS-1.5-7B, and attains 1.4x higher training efficiency than Single State Single Action methods PPO and GRPO at matched success rates.

📄 PDF Abstract BibTeX arXiv:2604.07277

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents

2025-09-10 · Yifan Xu, Xiao Liu, Xinghan Liu, Jiaqi Fu 외 arxiv

Building general-purpose graphical user interface (GUI) agents has become increasingly promising with the progress in vision language models. However, developing effective mobile GUI agents with reinforcement learning (R…

Reinforcement Learning

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

2026-07-02 · Jiayin Zhu, Kelong Mao, Yudong Guo, Dengbo He 외 arxiv

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use …

SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice

2026-06-02 · Tianfu Wang, Max Xiong, Jianxun Lian, Hongyuan Zhu 외 arxiv

Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and effective training remains a significant challenge due to the scar…

Reinforcement Learning

From Barriers to Tactics: A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching

2024-10-17 · Eric Yang, Tomas Garcia, Hannah Williams, Bhawesh Kumar 외

Effective management of cardiometabolic conditions requires sustained positive nutrition habits, often hindered by complex and individualized barriers. Direct human management is simply not scalable, while previous attem…

ManagementNutrition

Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems

2026-04-13 · Deeksha Prahlad, Daniel Fan, Hokeun Kim arxiv

Foundation models, including large language models (LLMs), are increasingly used for human-in-the-loop (HITL) cyber-physical systems (CPS) because foundation model-based AI agents can potentially interact with both the p…