CATArena (Code Agent Tournament Arena) is an open-ended environment where LLMs write executable code agents to battle each other and then learn from each other. CATArena is an engineering-level ...

Directly presenting final requirements to AI often leads to code generation that deviates from intended outcomes because the AI lacks human intervention during the development process. Without ...

Abstract: The quality of modern software relies heavily on the effective use of static code analysis tools. To improve their usefulness, these tools should be evaluated using a framework that ...

Abstract: The acquisition and reconstruction of seismic data are fundamental to seismic exploration. The balancing data quality and acquisition cost is essential. To address this challenge, we propose ...