Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.06982 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918049980874752 |
|---|---|
| author | Liu, Cong Wu, Jie Wu, Weigang Chen, Xu Lin, Liang Zheng, Wei-Shi |
| author_facet | Liu, Cong Wu, Jie Wu, Weigang Chen, Xu Lin, Liang Zheng, Wei-Shi |
| contents | Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data, which are typically absent in publicly available documents. This paper introduces the Chain of Methodologies (CoM), an innovative and intuitive prompting framework that enhances structured thinking by integrating human methodological insights, enabling LLMs to tackle complex tasks with extended reasoning. CoM leverages the metacognitive abilities of advanced LLMs, activating systematic reasoning throught user-defined methodologies without explicit fine-tuning. Experiments show that CoM surpasses competitive baselines, demonstrating the potential of training-free prompting methods as robust solutions for complex reasoning tasks and bridging the gap toward human-level reasoning through human-like methodological insights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chain of Methodologies: Scaling Test Time Computation without Training Liu, Cong Wu, Jie Wu, Weigang Chen, Xu Lin, Liang Zheng, Wei-Shi Computation and Language Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data, which are typically absent in publicly available documents. This paper introduces the Chain of Methodologies (CoM), an innovative and intuitive prompting framework that enhances structured thinking by integrating human methodological insights, enabling LLMs to tackle complex tasks with extended reasoning. CoM leverages the metacognitive abilities of advanced LLMs, activating systematic reasoning throught user-defined methodologies without explicit fine-tuning. Experiments show that CoM surpasses competitive baselines, demonstrating the potential of training-free prompting methods as robust solutions for complex reasoning tasks and bridging the gap toward human-level reasoning through human-like methodological insights. |
| title | Chain of Methodologies: Scaling Test Time Computation without Training |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.06982 |