Minimal Free Resolution Guided Adaptive Tree Reasoning

Dezhao Tang, Meihan Liu, Yulai Tong, Guan Yuan, Qiuyan Yan


Abstract
Dynamic reasoning trees can help large language models solve complex tasks by explicitly structuring intermediate decisions.However, existing approaches often rely on manually specified subproblems or predefined decomposition patterns, which limits the effectiveness of reasoning and generalization.To solve this problem, we propose SyRA, a hierarchical reasoning framework based on MFR theory that supports the construction of adaptive reasoning trees and reliable error correction within a single LLM. Specifically, SyRA focuses on reasoning-tree construction, dynamically controlling branching and expansion using MFR principles to enable informative, non-redundant subproblem decomposition. In addition, it introduces a residual backtracking mechanism for adaptive cross-layer error correction, allowing the model to revise earlier reasoning decisions based on downstream feedback.Across eight reasoning benchmarks, SyRA significantly reduces logical errors and improves reasoning accuracy, while achieving a better balance between accuracy and reasoning time than the Chain-of-Thought, Decompose–Analyze–Rethink and Tree-of-Thought. Our code and dataset are available at https://github.com/Tim798-art/SyRA/tree/main/SyRA.
Anthology ID:
2026.acl-long.2158
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46507–46522
Language:
URL:
https://aclanthology.org/2026.acl-long.2158/
DOI:
10.18653/v1/2026.acl-long.2158
Bibkey:
Cite (ACL):
Dezhao Tang, Meihan Liu, Yulai Tong, Guan Yuan, and Qiuyan Yan. 2026. Minimal Free Resolution Guided Adaptive Tree Reasoning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 46507–46522, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Minimal Free Resolution Guided Adaptive Tree Reasoning (Tang et al., ACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.acl-long.2158.pdf
Checklist:
 2026.acl-long.2158.checklist.pdf