连续GUI代理
Continual GUI Agents
AI总结：
本文提出连续GUI代理任务，通过引入GUI-Anchoring in Flux框架，解决GUI分布变化时持续学习稳定性问题，实验显示其优于现有方法。
摘要：
随着数字环境（数据分布）不断变化，新GUI数据随时间到来，引入新领域或分辨率，训练于静态环境的代理性能下降。本文提出连续GUI代理，要求GUI代理在领域和分辨率变化下持续学习。现有方法因UI交互点和区域多样性导致稳定接地失效。为此，引入GUI-Anchoring in Flux框架，通过两种新奖励：Anchoring Point Reward in Flux和Anchoring Region Reward in Flux，引导代理对齐变化的交互点和区域，缓解现有奖励策略过度适应静态接地线索的问题。大量实验表明GUI-AiF优于现有方法。本文建立了首个连续学习框架，揭示了强化微调在连续GUI代理中的潜力。
英文摘要：
As digital environments (data distribution) are in flux, with new GUI data arriving over time-introducing new domains or resolutions-agents trained on static environments deteriorate in performance. In this work, we introduce Continual GUI Agents, a new task that requires GUI agents to perform continual learning under shifted domains and resolutions. We find existing methods fail to maintain stable grounding as GUI distributions shift over time, due to the diversity of UI interaction points and regions in fluxing scenarios. To address this, we introduce GUI-Anchoring in Flux (GUI-AiF), a new reinforcement fine-tuning framework that stabilizes continual learning through two novel rewards: Anchoring Point Reward in Flux (APR-iF) and Anchoring Region Reward in Flux (ARR-iF). These rewards guide the agents to align with shifting interaction points and regions, mitigating the tendency of existing reward strategies to over-adapt to static grounding cues (e.g., fixed coordinates or element scales). Extensive experiments show GUI-AiF surpasses state-of-the-art baselines. Our work establishes the first continual learning framework for GUI agents, revealing the untapped potential of reinforcement fine-tuning for continual GUI Agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
