沉浸于惯性：面向计算机使用智能体的激活分析

中文摘要 AI 辅助

计算机使用智能体已日益能够通过自然语言指令，基于截图、动作和推理的轨迹，在真实桌面上执行任务。我们发现，它们可能隐蔽地表现出惯性，即尽管认识到某些动作无效，仍重复执行这些徒劳的动作。我们假设惯性反映在智能体的内部状态中，即其底层模型的激活值，并提出了一种协议来测量两者之间的关系。对高维激活状态的广泛分析表明，惯性对应于激活空间中的一个吸收区域，在该区域中，激活值在动作之间变得陈旧，甚至在尝试引导它们之后也是如此。我们推测，通过重新初始化来大幅改变智能体的激活是摆脱惯性的必要条件。具体而言，我们提出了R$^3$（重置、改道、恢复），该方法暂时重置智能体的上下文轨迹以逃离吸收区域，然后恢复历史上下文以有效完成任务。我们的方法在多个模型上将测得的惯性降低了17-55%。这些结果表明，改变上下文比直接引导所产生的激活更能有效地中断重复循环。我们的代码可在以下网址获取：https://this URL

英文摘要

Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, actions, and reasoning. We discover that they can stealthily exhibit inertia, in which they repeat fruitless actions despite recognizing that these actions are ineffective. We hypothesize that inertia is reflected in the agent's internal state, i.e., the activation values of the agent's underlying model, and propose a protocol to measure the relationship between the two. Extensive analysis of high-dimensional activation states shows that inertia corresponds to an absorbing region of activation space, where activation values become stale across actions and even after attempts to steer them. We conjecture that drastically changing the agents' activations by re-initializing them is necessary to escape inertia. Specifically, we propose R$^3$ (Reset, Reroute, Restore), which temporarily resets the agent's context trajectory to escape the absorbing region and then restores the historical context to effectively complete the task. Our approach yields 17-55% lower measured inertia across models relative to unmodified agents. These results suggest that changing the context can interrupt recurrence more effectively than directly steering the resulting activations. Our code is available at https://anonymous.4open.science/r/vlm-agent-defense-D076

发表机构

• Université de Neuchâtel（纳沙泰尔大学）
• Delft University of Technology（代尔夫特理工大学）

机构由 AI 辅助整理，请以论文原文为准。