LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents· LEASH: 计算机使用代理的不确定性感知弱转强升级与监督
Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Weak-to-strong escalation offers a middle ground where a weak agent acts by default and hands control to a strong one only when needed. The core challenge is deciding when to escalate, which requires an uncertainty signal cheap enough to check at every step. However, even after handoff, the strong agent can still get lost, but a black-box API that the strong agent is usually served exposes no internals to monitor. To this end, we propose LEASH, a training-free framework that unleashes the strong agent only when the weak agent's latent uncertainty signals it is needed, and keeps it on a leash afterward. LEASH has three layers:
提出 LEASH 框架，根据弱代理的不确定性信号决策升级至强代理。
- 核心方法
- LEASH 框架通过检测弱代理的潜在不确定性信号来决定是否升级到强代理，并在升级后继续监督强代理的动作。
- 适合谁读
- 适合研究者和工程师阅读，尤其是关注代理系统优化和资源管理的读者。
- 要解决的问题
- 解决长期任务中弱代理频繁需升级至强代理及其后续监督的问题。
- 关键实验
- 通过一系列长期任务的模拟实验，验证了 LEASH 在不同类型任务中的有效性和适应性。
- 主要贡献
- 提供了一个无训练的框架，有效减少了强代理的调用次数以及提高了任务完成的质量和效率。
- 意义与局限
- LEASH 框架对提升计算机使用代理在长期任务中的性能具有重要意义，但其依赖弱代理的不确定性信号可能在某些情况下不够准确。