Search papers, labs, and topics across Lattice.
5
0
8
22
Coding agent benchmarks can now dynamically scale difficulty and avoid data leakage by having agents evaluate each other, with the latest models generating tasks that defeat older solvers 10x more often.
Vulnerabilities spanning multiple functions can be detected more accurately with VulAgentRL, which verifies evidence through a novel Code Property Graph approach.
LLM agents are not just chatbots: they can find hundreds of real-world software vulnerabilities that traditional tools miss.
Multimodal LLMs can reconstruct and analyze cyber-physical system architectures from fragmented documentation, enabling more accurate security assessments.
Security patch detectors trained on standard vulnerability databases are practically useless in the real world, losing up to 90% F1-score when deployed on in-the-wild data.
