作者位次 #2/6ACL 2026OralOutstanding Paper· Natural Language Processing
CURE : Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement
Guirong Chen · Shuqi Ye · Wenkai Yang · Shiqi Shen · Guangyao Shen · Yankai Lin
摘要
The evolution paradigm of Large Language Models (LLMs) is shifting from scaling training compute to scaling inference-time compute. While Reinforcement Learning with Verifiable Rewards (RLVR) has become a key engine for this transition, standard approaches often fail to equip models with the auto...