Search papers, labs, and topics across Lattice.
Virtue AI, University of California, Santa Barbara
3
0
4
10
Shapley-guided analysis reveals hidden vulnerabilities in multi-agent systems, enabling targeted and coordinated adversarial attacks that traditional methods miss.
A unified assessment framework reveals hidden insights about agent performance, transforming how we evaluate AI systems.
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
