作者位次 #3/5ACL 2026Findings· Findings of ACL
C on MA : Confidence-Guided Kernel Sampling with Multi-Stage Aggregation for LLM Reasoning
Yinuo Wang · Qingjie Li · Wenyao Cui · Qiuchi Li · Zhang Huaping
摘要
Test-time scaling (TTS) enhances LLM reasoning capabilities by sampling and aggregating diverse solution trajectories. However, existing approaches often rely on external verifiers and one-shot independent sampling, which results in inefficient budget allocation and underutilizes interim high-qua...