<ul data-eligibleForWebStory="true"><li>Test-time compute scaling aims to improve model accuracy by using additional computation at inference time.</li><li>Efficient Tree Search (ETS) is proposed to address challenges in search methods for inference-time scaling.</li><li>ETS uses a process reward model to generate and score potential candidates during the search process.</li><li>Increasing diversity in trajectories during tree search promotes more exploration but consumes more memory.</li><li>ETS promotes KV sharing by pruning redundant trajectories while maintaining necessary diversity.</li><li>A linear programming cost model in ETS penalizes the number of retained nodes to promote KV cache sharing.</li><li>ETS achieves a 1.8$	imes$ reduction in average KV cache size during search, leading to 1.4$	imes$ increased throughput.</li><li>ETS demonstrates improved performance relative to prior state-of-the-art methods with minimal accuracy degradation.</li><li>No custom kernel implementation is required for ETS, and the code is available on GitHub.</li></ul>

ETS: Efficient Tree Search for Inference-Time Scaling

Discover more