Abstract: Software quality assessment is inherently a multi-objective problem, involving trade-offs among factors such as functionality, reliability, performance, maintainability, and security.

Very large-scale integration (VLSI) floorplanning is a fundamental task in the design automation of integrated circuits. It involves determining optimal positions for functional modules on a chip, ...

Are AI tools reliable enough to be used at in commercial settings? If so, should they be given “autonomy” to make decisions? These are the questions being raised after at least two internet outages at ...

We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 ...