作者位次 #7/7ACL 2026Poster· Natural Language Processing
Behavior Knowledge Merge in Reinforced Agentic Models
Xiangchi Yuan · Dachuan Shi · Chunhui Zhang · Zheyuan Liu · Shenglong Yao · Soroush Vosoughi · Wenke Lee
摘要
Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents from different tasks into a single generalist model. Howeve...