用树搜索统一生成、探索与评估，提升电脑操作智能体的规划能力。
Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
- 在每一步使用蒙特卡洛树搜索，动态规划下一步动作
- 在OSWorld上达到77%成功率，显著优于同类方法
- 适合需要高可靠性的自动化任务场景
尽管通过轨迹级采样提升测试时计算量已显著改善图形用户界面（GUI）智能体的表现，但缺乏回溯能力导致部分成功无法复用，也无法从早期错误中恢复。本文提出Agent Alpha，一种通过步骤级蒙特卡洛树搜索（MCTS）统一生成、探索与评估的框架。该框架集成alpha-UCT引导的搜索机制，实现主动建模或利用规划空间结构，支持早期剪枝次优分支并高效重用前缀。采用对比驱动的评估策略以缓解绝对评分偏差，结合多样性约束扩展策略保持搜索空间紧凑且信息丰富。分析了alpha-UCT的遗憾边界。在OSWorld基准上，Agent Alpha实现约77%的成功率，在同等计算资源下显著超越轨迹级基线。
原文摘要 · Abstract (English)
While scaling test-time compute through trajectory-level sampling has significantly improved Graphical User Interface (GUI) agents, the lack of regressive ability prevents the reuse of partial successes and the recovery from early missteps. In this paper, we introduce Agent Alpha, a unified framework that synergizes generation, exploration, and evaluation through step-level Monte Carlo Tree Search (MCTS). It enables active modeling or exploiting structures of the planning space. By integrating alpha-UCT guided search into the interaction loop, Agent Alpha enables deliberate planning, facilitating early pruning of suboptimal branches and efficient prefix reuse. We also employ comparison-driven evaluation to mitigate absolute scoring biases and diversity-constrained expansion to maintain a compact, informative search space. Regret bound of alpha-UCT is analyzed. On the OSWorld benchmark, Agent Alpha achieves a state-of-the-art success rate of $\sim 77\%$, significantly outperforming trajectory-level baselines under equivalent compute.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。