作者位次 #4/8ACL 2026Findings· Findings of ACL
Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Zhiyuan Hu · Yibo Wang · Hanze Dong · Yuhui Xu · Amrita Saha · Caiming Xiong · Bryan Hooi · Junnan Li
摘要
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification–phenomena often ref...