AI-SOVEREIGN
Home / AI Research / Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement
PIAI Research

Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement

by agentscope-ai · Zhenqing Ling, Qirui Jiao, Daoyuan Chen, Cheng Chen, Xinji Mai, Haowen Gao

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 harnesses, data workflows, and interactive games. Piccolo-27B tops the Decision Index Vision Full leaderboard with a score of 75.59, while Piccolo-9B and Piccolo-4B achieve 68.35 and 67.46, respectively. All three rank first on the Private benchmark in their respective model-size categories. Research agents analyze model behavior, construct training data, conduct experiments, and use the…

Upvotes14
Comments2
Published17 Nov 2026

More from agentscope-ai