Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning - researchr publication

researchr

You are not signed in
Sign in
Sign up

Zhiyin Yu, Bo Zhang 0069, Qibin Hou, Zhonghai Wu, Xiao Luo 0001, Lei Bai 0001. Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 15780-15795, Association for Computational Linguistics, 2026. [doi]

Abstract is missing.

runs on WebDSL