作者位次 #6/11ACL 2026Findings· Findings of ACL
Supplement Generation Training for Enhancing Agentic Task Performance
Young Min Cho · Daniele Bonadiman · Divya Bhargavi · Tamer Alkhouli · Salvatore Romeo · Dongwei Jiang · Khushbu Pahwa · Yubin Ge · Etsuko Ishii · Monica Sunkara · Yi Zhang
摘要
Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Ge...