Effective tool use and reasoning are essential capabilities for large reasoning models~(LRMs) to address complex real-world problems. Through empirical analysis, we identify that current LRMs lack the capability of sub-task decomposition in complex tool use scenarios, leading to Lazy Reasoning. To address this, we propose a two-stage training framework D-CORE~(\underline{\textbf{D}}ecomposing tasks and \underline{\textbf{Co}}mposing \underline{\textbf{Re}}asoning processes) that first incentivize the LRMs' task decomposition reasoning capability via self-distillation, followed by diversity-aware reinforcement learning~(RL) to restore LRMs' reflective reasoning capability. D-CORE achieves robust tool-use improvements across diverse benchmarks and model scales. Experiments on BFCLv3 demonstrate superiority of our method: D-CORE-8B reaches 77.7\% accuracy, surpassing the best-performing 8B model by 5.7\%. Meanwhile, D-CORE-14B establishes a new state-of-the-art at 79.3\%, outperforming 70B models despite being 5× smaller. The source code is available at https://github.com/alibaba/EfficientAI.
@article{arxiv.2602.02160,
title = {D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use},
author = {Bowen Xu and Shaoyu Wu and Hao Jiang and Kai Liu and Xin Chen and Lulu Hu and Bin Yang},
journal= {arXiv preprint arXiv:2602.02160},
year = {2026}
}