KG-Augmented Executable CoT for Mathematical Coding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915430469206016 |
|---|---|
| author | Chen, Xingyu An, Junxiu Guo, Jun Wang, Li Guo, Jingcai |
| author_facet | Chen, Xingyu An, Junxiu Guo, Jun Wang, Li Guo, Jingcai |
| contents | In recent years, large language models (LLMs) have excelled in natural language processing tasks but face significant challenges in complex reasoning tasks such as mathematical reasoning and code generation. To address these limitations, we propose KG-Augmented Executable Chain-of-Thought (KGA-ECoT), a novel framework that enhances code generation through knowledge graphs and improves mathematical reasoning via executable code. KGA-ECoT decomposes problems into a Structured Task Graph, leverages efficient GraphRAG for precise knowledge retrieval from mathematical libraries, and generates verifiable code to ensure computational accuracy. Evaluations on multiple mathematical reasoning benchmarks demonstrate that KGA-ECoT significantly outperforms existing prompting methods, achieving absolute accuracy improvements ranging from several to over ten percentage points. Further analysis confirms the critical roles of GraphRAG in enhancing code quality and external code execution in ensuring precision. These findings collectively establish KGA-ECoT as a robust and highly generalizable framework for complex mathematical reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KG-Augmented Executable CoT for Mathematical Coding Chen, Xingyu An, Junxiu Guo, Jun Wang, Li Guo, Jingcai Artificial Intelligence In recent years, large language models (LLMs) have excelled in natural language processing tasks but face significant challenges in complex reasoning tasks such as mathematical reasoning and code generation. To address these limitations, we propose KG-Augmented Executable Chain-of-Thought (KGA-ECoT), a novel framework that enhances code generation through knowledge graphs and improves mathematical reasoning via executable code. KGA-ECoT decomposes problems into a Structured Task Graph, leverages efficient GraphRAG for precise knowledge retrieval from mathematical libraries, and generates verifiable code to ensure computational accuracy. Evaluations on multiple mathematical reasoning benchmarks demonstrate that KGA-ECoT significantly outperforms existing prompting methods, achieving absolute accuracy improvements ranging from several to over ten percentage points. Further analysis confirms the critical roles of GraphRAG in enhancing code quality and external code execution in ensuring precision. These findings collectively establish KGA-ECoT as a robust and highly generalizable framework for complex mathematical reasoning tasks. |
| title | KG-Augmented Executable CoT for Mathematical Coding |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.04072 |