APA (7th ed.) Citation

Yadav, S., Yadav, S., & Goyal, P. (2026). Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs.

Chicago Style (17th ed.) Citation

Yadav, Suraj, Siddharth Yadav, and Parth Goyal. Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs. 2026.

MLA (9th ed.) Citation

Yadav, Suraj, et al. Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs. 2026.