Tag
MintAct is a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual tool use, achieving state-of-the-art performance on various benchmarks.
RSIAgent is a training-free multi-agent framework that enables digital agents to adapt to new environments through recursive self-improvement, autonomous memory construction, and broad-then-deep exploration, outperforming closed-source models on benchmarks.
The article argues that the real shift in AI is not just productivity gains, but the move from direct use of software to delegating tasks to AI representatives that act on our behalf, raising questions about data intimacy and trust.