Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
2
0
4
1
LLM agents acting in the real world introduce a whole new threat landscape beyond unsafe text, demanding a shift in focus towards system-level security for agent ecosystems.
GUI agents learn faster and generalize better with a new reward shaping technique that dynamically adapts to successful exploration trajectories, outperforming fixed reward schemes.
