APA (7th ed.) Citation

Ran-Milo, Y., Alexander, Y., Mendel, S., & Cohen, N. (2026). Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data.

Chicago Style (17th ed.) Citation

Ran-Milo, Yuval, Yotam Alexander, Shahar Mendel, and Nadav Cohen. Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data. 2026.

MLA (9th ed.) Citation

Ran-Milo, Yuval, et al. Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data. 2026.