作者位次 #4/8ACL 2026Findings· Findings of ACL
M eta S cale: Test-Time Scaling with Evolving Meta-Thoughts
Qin Liu · Wenxuan Zhou · Nan Xu · James Y. Huang · Fei Wang · Sheng Zhang · Hoifung Poon · Muhao Chen
摘要
One critical challenge for large language models (LLMs) in making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a given task. Existing approaches impose fixed cognitive struc...