Search papers, labs, and topics across Lattice.
3
0
3
0
Achieving an 86.17% success rate in reproduction test generation, DPIAgent reveals that structured task separation can dramatically enhance performance in automated software engineering.
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.
