AI RESEARCH
One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
arXiv CS.LG
•
ArXi:2601.03111v2 Announce Type: replace The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI, 2025a; Zeng, 2025). The success of existing RL attempts in LLMs usually rely on high-quality samples of large volumes. In this paper, we challenge conventional assumptions about data requirements in RL for LLMs by nstrating the effectiveness of one-shot reinforcement learning. Specifically, we