Search papers, labs, and topics across Lattice.
3
0
4
Real-world GUI agents can achieve over 72% success in complex mobile tasks by leveraging a unique hybrid training approach that integrates real-device execution and adaptive learning from failures.
RL fine-tuning on a massive new mobile GUI dataset closes the sim2real gap, outperforming supervised methods and suggesting a path to more robust vision-language agents.
Current mobile GUI agents struggle with complex, long-horizon tasks in realistic simulated environments, achieving only a 17.82% success rate on SimuWoB.
