Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.08595 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914184542814208 |
|---|---|
| author | Kim, Joongho Huang, Xirui Reza, Zarreen Grand, Gabriel |
| author_facet | Kim, Joongho Huang, Xirui Reza, Zarreen Grand, Gabriel |
| contents | Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce Semantic Similarity-Based Dynamic Pruning (SSDP), a lightweight method that, to the best of our knowledge, is the first framework to integrate online semantic merging into parallelized tree search, enabling the clustering and pruning of redundant steps in real time. Across reasoning benchmarks, including GSM8K and MATH500, SSDP achieves up to a 2.3x speedup over state-of-the-art tree-search baselines while maintaining competitive accuracy (typically within 5% of the strongest baseline) and reducing the number of explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning. The implementation of SSDP is publicly available at https://github.com/kimjoonghokim/SSDP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning Kim, Joongho Huang, Xirui Reza, Zarreen Grand, Gabriel Computation and Language Artificial Intelligence Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce Semantic Similarity-Based Dynamic Pruning (SSDP), a lightweight method that, to the best of our knowledge, is the first framework to integrate online semantic merging into parallelized tree search, enabling the clustering and pruning of redundant steps in real time. Across reasoning benchmarks, including GSM8K and MATH500, SSDP achieves up to a 2.3x speedup over state-of-the-art tree-search baselines while maintaining competitive accuracy (typically within 5% of the strongest baseline) and reducing the number of explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning. The implementation of SSDP is publicly available at https://github.com/kimjoonghokim/SSDP. |
| title | Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.08595 |