Hark 发布 Handoff²,computer-use agent 速度提升 2 倍
Hark Releases Handoff², a 2x Faster Computer-Use Agent for Hark Pro
做网页自动化的人可以关注这个:Hark 把 computer-use agent 的速度翻倍,方法是用带延迟惩罚的强化学习让模型学会批量操作,478 个任务跑出 82% 完成率。相比 Operator 这类逐点击的方案,这个思路值得借鉴。
Hark 为其 Hark Pro 产品发布 Handoff²,这是其 computer-use agent 的第二代版本,平均执行速度比 v1 快 2 倍。在内部测试中,Handoff² 在 478 个真实网页操作任务上完成率为 82%。速度提升的核心来自训练方式的改变:模型通过带延迟惩罚的强化学习(latency-penalized RL),学会了把多个操作批量执行,减少不必要的逐步等待。
从机制上看,传统 computer-use agent 通常逐步点击、输入、等待页面响应,而 Handoff² 在 RL 训练中被直接惩罚响应延迟,因此自发学到了动作合并策略。这种以延迟为奖励信号一部分的训练方式,说明 agent 的效率可以通过训练目标显式优化,而非仅靠底层模型升级。
在竞争语境下,computer-use agent 赛道已有 OpenAI 的 Operator、Anthropic 的 computer use 能力等玩家,Hark 选择用速度和任务完成率作为差异化指标。对需要自动化网页流程的企业用户来说,82% 的完成率意味着约五分之一的任务仍需人工接管,实际部署时仍需保留人工兜底流程。
Hark Releases Handoff², a 2x Faster Computer-Use Agent for Hark Pro
Hark has released Handoff², the computer-use agent inside Hark Pro. It averages 2x faster than v1, completes 82% of 478 internal web tasks, and learned to batch actions through latency-penalized RL. The post Hark Releases Handoff², a 2x Faster Computer-Use Agent for Hark Pro appeared first on MarkTechPost .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Hark, Handoff², computer-use agent, agents.
Primary source verification: published directly by marktechpost with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including Aravind Srinivas, swyx (AI Engineer), AIGCLINK), confirming industry-wide signal strength.