Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
Xiaolong Wei, Yuehu Dong, Xingliang Wang, Xingyu Zhang, Zhejun Zhao, Dongdong Shen, Long Xia, Dawei Yin
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
BibTeX
@inproceedings{aaai2026_beyondreactaplan,
title = {Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning},
author = {Xiaolong Wei and Yuehu Dong and Xingliang Wang and Xingyu Zhang and Zhejun Zhao and Dongdong Shen and Long Xia and Dawei Yin},
booktitle = {AAAI 2026},
year = {2026}
}