Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24663 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914119015202816 |
|---|---|
| author | Lu, Yifu Liu, Shengjie Dong, Li |
| author_facet | Lu, Yifu Liu, Shengjie Dong, Li |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24663 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OrchDAG: Complex Tool Orchestration in Multi-Turn Interactions with Plan DAGs Lu, Yifu Liu, Shengjie Dong, Li Artificial Intelligence 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. |
| title | OrchDAG: Complex Tool Orchestration in Multi-Turn Interactions with Plan DAGs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.24663 |