Search for a command to run...
Learnings From the Trenches Every enterprise software company is asking some version of the same question: How do we use AI agents to ship faster and unlock new customer value without putting our miss
Goal Our goal in this study was to explore whether a mixture of open-weight models, combined through an iterative process, can outperform any single model on the SWE-bench Verified benchmark. Specifically, we wanted to evaluate if patches generated b...
Abstract This study presents a comprehensive analysis of SWE-agent trajectories comparing Kimi K2 Instruct and Claude Sonnet 4 performance on software engineering tasks from the SWE-bench dataset. Through detailed examination of action category distr...
