Agentic tool use has gained traction with the rise of agentic tool calling, yet most existing work overlooks the complexity of multi-turn tool interactions. We introduce OrchDAG, a synthetic data generation pipeline that models tool execution as directed acyclic graphs (DAGs) with controllable complexity. Using this dataset, we benchmark model performance and propose a graph-based reward to enhance RLVR training. Experiments show that the dataset presents a challenging but solvable benchmark, and the proposed reward is effective when combined with GRPO-style algorithms, highlighting the importance of leveraging topological structure and data complexity in multi-turn tool use.
@article{arxiv.2510.24663,
title = {OrchDAG: Complex Tool Orchestration in Multi-Turn Interactions with Plan DAGs},
author = {Yifu Lu and Shengjie Liu and Li Dong},
journal= {arXiv preprint arXiv:2510.24663},
year = {2025}
}