Author name: Xinyi Gao, Xinyu Ren, Junliang Yu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin

arXiv:2605.11706v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices with subtask intent wh…