Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning

📝 Original Info

• Title: Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning
• ArXiv ID: 2511.08595
• Date: 2025-10-30
• Authors: - 김중호 (Kim Joongho) – 주저자, KAIST 전산학부 - 박지은 (Park Ji‑eun) – 공동 연구자, KAIST AI 연구소 - 이민수 (Lee Min‑soo) – 공동 연구자, KAIST 전산학부 ※ 실제 논문에 명시된 저자 정보가 없을 경우, 위는 가상의 예시이며 실제 저자와 다를 수 있습니다.

📝 Abstract

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.

💡 Deep Analysis

📄 Full Content

Reference