Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering
arXiv preprint, 2026
Abstract
Machine learning engineering tasks demand extended decision-making cycles that stretch far beyond the horizon a single agent can reliably manage. Matryoshka Agent decomposes agentic problem solving into a coordinated hierarchy: an Orchestrator maintains high-level strategy and delegates, while Sub-Agents unfold to execute concrete, bounded tasks and report back. This separation keeps the Orchestrator’s context focused on strategy rather than execution detail, allowing the system to sustain long-horizon workflows. The framework enables Qwen3-4B-Instruct to reach Orchestrator performance comparable to o4-mini, and delivers up to 36.7% performance gains when paired with larger backbone models.
Materials
BibTeX
@misc{qiang2026matryoshkaagentunfoldingsubagents,
title={Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering},
author={Rushi Qiang and Changhao Li and Haotian Sun and Yuchen Zhuang and Chao Zhang and Bo Dai},
year={2026},
eprint={2607.25090},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2607.25090},
}