Skip to content
NeurIPS 2026 planner

Poster · Paris

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data

When
Fri 11 Dec 2026, 11:30–13:30 CET
Where
Paris Poster Hall
Session
Paris Poster Session 5
Authors
Yuval Ran-Milo, ‪Yotam Alexander‬‏, Shahar Mendel, Nadav Cohen
Organisations
Tel Aviv University
QRS classification
Reinforcement learning, Attention and transformers, Language models

Open in scheduleOfficial page