Monte Carlo Tree Search (MCTS) is an effective test-time compute scaling (TTCS) method for improving the reasoning performance of large language models, but its highly variable execution time leads to severe long-tail latency in practice. Existing optimizations such as positive early exit, reduce latency in favorable cases but are less effective when search continues without meaningful progress. We introduce {\it negative early exit}, which prunes unproductive MCTS trajectories, and an {\it adaptive boosting mechanism} that reallocates reclaimed computation to reduce resource contention among concurrent searches. Integrated into vLLM, these techniques substantially reduce p99 end-to-end latency while improving throughput and maintaining reasoning accuracy.
@article{arxiv.2604.00510,
title = {Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling},
author = {Hongbeen Kim and Juhyun Lee and Sanghyeon Lee and Kwanghoon Choi and Jaehyuk Huh},
journal= {arXiv preprint arXiv:2604.00510},
year = {2026}
}