{"ID":2842122,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10037","arxiv_id":"2511.10037","title":"Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning","abstract":"Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimization traps due to their reliance on incremental decision-making processes. To address these limitations, we propose a novel Planner-centric Plan-Execute paradigm that fundamentally resolves local optimization bottlenecks through architectural innovation. Central to our approach is a novel Planner model that performs global Directed Acyclic Graph (DAG) planning for complex queries, enabling optimized execution beyond conventional tool coordination. We also introduce ComplexTool-Plan, a large-scale benchmark dataset featuring complex queries that demand sophisticated multi-tool composition and coordination capabilities. Additionally, we develop a two-stage training methodology that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), systematically enhancing the Planner's tool selection accuracy and global planning awareness through structured DAG-based planning. When integrated with a capable executor, our framework achieves state-of-the-art performance on the StableToolBench benchmark for complex user queries, demonstrating superior end-to-end execution capabilities and robust handling of intricate multi-tool workflows.","short_abstract":"Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimization traps due to their reliance on incremental decision-making processes. To address these limitations, we propose a novel Planner-centric P...","url_abs":"https://arxiv.org/abs/2511.10037","url_pdf":"https://arxiv.org/pdf/2511.10037v2","authors":"[\"Xiaolong Wei\",\"Yuehu Dong\",\"Xingliang Wang\",\"Xingyu Zhang\",\"Zhejun Zhao\",\"Dongdong Shen\",\"Long Xia\",\"Dawei Yin\"]","published":"2025-11-13T07:22:27Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}