Saved in:
Bibliographic Details
Main Authors: Lu, Yifu, Liu, Shengjie, Dong, Li
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