Code & Software Engineering

Caper pre-executes each proposed shell command in a snapshotted sandbox, gives an LLM approver a bounded effects report, commits allowed commands, and rolls back blocked ones with a reason.

SWE-Trail uses prior attempts as collector-side history to choose where to compare candidate actions during coding-agent rollouts, then trains students on the resulting trajectories.

CrossSWE is a 171-instance benchmark for cross-repository joint development, where tasks require coordinated changes across interdependent repositories and are verified by joint-necessity testing.

CodeSpecWeave synthesizes coding tasks with interdependent specifications and reliable executable tests, producing 4,670 training tasks and a 100-task benchmark.

VibeGame couples an AI-native 2D game engine with an eight-agent adversarial team and training-free experience distillation to turn natural-language prompts into playable game projects.