Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

ArXi:2605.15100v1 Announce Type: new Large Language Models (LLMs) have nstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains.