Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement Piccolo, a family of multimodal decision models ranging from 0.8B to 27B parameters, co-evolves model capabilities and training data through Agentic Data Engineering and recursive self-improvement, according to the model's presentation. The Piccolo models predict probabilities over candidate answers for general-purpose text and visual judgments and agent tasks. We present Piccolo, a family of multimodal decision models 0.8B to 27B that coevolves model capabilities and training data via Agentic Data Engineering and recursive self-improvement RSI . The models predict probabilities over candidate answers for general-purpose text and visual judgments, agent