Saved in:
Bibliographic Details
Main Authors: Ta, Tung Duong, Oates, Tim, Van Luong, Thien, Vu, Huan, Nguyen, Tien Cuong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.18841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914222995144704
author Ta, Tung Duong
Oates, Tim
Van Luong, Thien
Vu, Huan
Nguyen, Tien Cuong
author_facet Ta, Tung Duong
Oates, Tim
Van Luong, Thien
Vu, Huan
Nguyen, Tien Cuong
contents Despite advances in mathematical reasoning capabilities, Large Language Models (LLMs) still struggle with calculation verification when using established prompting techniques. We present MDToC (Metacognitive Dynamic Tree of Concepts), a three-phase approach that constructs a concept tree, develops accuracy-verified calculations for each concept, and employs majority voting to evaluate competing solutions. Evaluations across CHAMP, MATH, and Game-of-24 benchmarks demonstrate our MDToC's effectiveness, with GPT-4-Turbo achieving 58.1\% on CHAMP, 86.6\% on MATH, and 85\% on Game-of-24 - outperforming GoT by 5\%, 5.4\%, and 4\% on all these tasks, respectively, without hand-engineered hints. MDToC consistently surpasses existing prompting methods across all backbone models, yielding improvements of up to 7.6\% over ToT and 6.2\% over GoT, establishing metacognitive calculation verification as a promising direction for enhanced mathematical reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18841
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language Models
Ta, Tung Duong
Oates, Tim
Van Luong, Thien
Vu, Huan
Nguyen, Tien Cuong
Computation and Language
Despite advances in mathematical reasoning capabilities, Large Language Models (LLMs) still struggle with calculation verification when using established prompting techniques. We present MDToC (Metacognitive Dynamic Tree of Concepts), a three-phase approach that constructs a concept tree, develops accuracy-verified calculations for each concept, and employs majority voting to evaluate competing solutions. Evaluations across CHAMP, MATH, and Game-of-24 benchmarks demonstrate our MDToC's effectiveness, with GPT-4-Turbo achieving 58.1\% on CHAMP, 86.6\% on MATH, and 85\% on Game-of-24 - outperforming GoT by 5\%, 5.4\%, and 4\% on all these tasks, respectively, without hand-engineered hints. MDToC consistently surpasses existing prompting methods across all backbone models, yielding improvements of up to 7.6\% over ToT and 6.2\% over GoT, establishing metacognitive calculation verification as a promising direction for enhanced mathematical reasoning.
title MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2512.18841