StepFun Open Sources onPanda to Cut LLM Annotation Time by 52%

The application allows users to view token probabilities and top-k alternatives to debug agent tasks and SVG generation. onPanda maintains a perplexity difference of less than 1% against the model's resampling baseline to ensure high on-policy fidelity. StepFun developed the tool over two years to facilitate precise control over how models and agents generate responses.