WeaveBench:面向计算机使用智能体的长时域混合界面基准
阅读原文· arxiv.orgWeaveBench 包含 114 个任务,覆盖 8 个真实工作领域,要求智能体在单次轨迹中结合 GUI 操作、CLI 与代码执行。评估在真实 Ubuntu 桌面进行,并设计了轨迹感知评判器以检测伪造视觉证据等捷径。前沿模型-运行时组合的最佳 PassRate 仅为 41.2%,表明基准远未饱和;仅依据结果评分会显著高估智能体性能。该基准揭示了当前计算机使用智能体评估的关键缺口。
Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, WeaveBench exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.