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

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 integrates online semantic merging into parallelized tree search to cluster and prune redundant steps in real time. Across GSM8K and MATH500 benchmarks with multiple LLMs (Llama-3, Qwen2.5), SSDP achieves up to a 2.5x speedup over state-of-the-art baselines while maintaining accuracy and reduces explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning.