Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
12
The rapid evolution of GUI agents is overshadowed by significant engineering shortcomings that threaten their real-world applicability.
Refinement complexity in automotive requirements is driven more by architectural scope than by linguistic verbosity, revealing critical insights for improving product development efficiency.
Prompt injection remains the leading attack vector against LLM agents, but emerging threats like persistent state corruption demand urgent attention.
Agent-generated feedback not only enhances report quality but also improves task performance and knowledge transfer in crowdsourced testing environments.
LLMs can be taught to avoid repeating past mistakes in vulnerability repair, boosting performance by up to 39% over state-of-the-art methods.
