Search papers, labs, and topics across Lattice.
4
0
2
8
Mobile application repair performance varies dramatically across LLM agents, with success rates ranging from 22% to 90% depending on the evaluator used.
OdinEval reveals that even in niche programming languages, LLMs can achieve impressive repair accuracy, with top models scoring over 66% in resolving defects.
KQFuzz uncovers bugs in quantum libraries with 18.44% better coverage than existing methods, revealing critical flaws that developers can quickly address.
LLMs can compile GUI code, but can't actually *play* it, highlighting a critical gap in their ability to generate logically correct, interactive applications.
