VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
Published in TMLR 2026 · Best Paper Award @ SPOT Workshop, ICLR 2026, 2025
Recommended citation: Dongfu Jiang*, Yi Lu*, Zhuofeng Li*, Zhiheng Lyu*, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen (2025). VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use. TMLR 2026. https://arxiv.org/abs/2509.01055
VerlTool is a unified and easy-to-extend tool-agent training framework based on verl, supporting agentic reinforcement learning with tool use across code execution, search, SQL, and software-engineering environments. The paper was accepted at TMLR 2026 and received the Best Paper Award at the SPOT Workshop @ ICLR 2026.
Zhiheng is a co-first author and core developer, responsible for the stateful environment interaction protocol and the SWE agent training pipeline.
Recommended citation:
@article{jiang2025verltool,
title={VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use},
author={Jiang, Dongfu and Lu, Yi and Li, Zhuofeng and Lyu, Zhiheng and Nie, Ping and Wang, Haozhe and Su, Alex and Chen, Hui and Zou, Kai and Du, Chao and Pang, Tianyu and Chen, Wenhu},
journal={arXiv preprint arXiv:2509.01055},
year={2025}
}