Tag
This paper from MIT and Harvard explores automating SKILL.md generation by mining GUI interaction trajectories, finding that clusters are readable but do not improve policy performance across domains.
PreAct compiles successful agent runs into small state-machine programs, enabling 8.5-13x faster replay on repeated tasks without per-step language model calls, with runtime screen checks to ensure correctness.
PreAct compiles successful task runs of computer-using agents into small state-machine programs, allowing fast replay (8.5–13× faster) on repeated tasks by skipping per-step language model calls, while verifying screen states at each step and falling back to the agent when mismatches occur.
SaaS-Bench is a new benchmark built on 23 deployable SaaS systems across six professional domains, containing 106 long-horizon tasks for evaluating computer-using agents. Experiments show that even the strongest models complete fewer than 4% of tasks end-to-end, highlighting significant limitations in current agent capabilities.