cs.CLNov 18, 2026

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

Authors: Zhenqing Ling, Qirui Jiao, Daoyuan Chen, Cheng Chen, Xinji Mai, Haowen Gao, Zhuo Zhang, Xuchen Pan, 

Abstract

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 results to refine subsequent proposals. Semantic slices and a shared research memory connect these actions across the model family's development. With training recipes comprising hundreds of thousands of examples, data selection and feedback-driven refinement are central to the self-improvement process. Our large-scale RSI exploration yields three counter-intuitive insights for decision-model development: (1) Backbone-recipe co-adaptation outweighs raw model recency: earlier backbones can surpass newer generations on visual tasks under identical recipes; (2) Targeted data curation enables 4B-9B models to rival 27B baselines on specialized workflows; and (3) Continuous loss reduction can decouple from and even degrade discrete decision accuracy. Together with the released weights and tools from the Data-Juicer and AgentScope ecosystems, Piccolo provides an actionable blueprint for building frontier decision models and scaling data-driven RSI.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Gödel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement

    Sep 29, 2026Ziqi Zhao, Fanqing Meng, Haocheng Lu +4Language Model Self-ImprovementRecursive Self-Improvement

  2. RSI-Prime: Training Models to Train Models

    Nov 17, 2026Dewu Zheng, Yang Ye, Hongyu Zhang +2Language Model Self-ImprovementLLM Post-Training

  3. Training LLM Agents to Automate LLM Post-Training with RSI-Dojo

    Oct 29, 2026Shuzheng Gao, Zhaojian Yu, Penghao Yin +4LLM Post-TrainingLLM Agent Self-Improvement