Search papers, labs, and topics across Lattice.
East China Normal University & Shanghai Innovation Institute
3
0
5
3
LLMs' impressive code generation skills crumble when faced with the messy reality of ambiguous requirements, highlighting a critical gap in their ability to handle real-world software development scenarios.
LLMs can help automated mobile app testing break free from UI "tarpits," leading to 50% higher code coverage and the discovery of dozens of previously unknown bugs in real-world apps.
LLM-based multi-agent systems are riddled with hidden failure modes that traditional testing misses, but FLARE uncovers them with coverage-guided fuzzing.
