Does Reward Training Teach AI New Reasoning? A New Paper Says No. Checked and Re-Run

By Sofia Reyes A new workshop paper argues that the training method behind today’s reasoning models, reinforcement learning with verifiable rewards, does not teach a model new reasoning. “RLVR Sharpens the Pencil, Not the Mind” by Shreeyam Bangera and Manya Gupta of IIT Roorkee (arXiv:2611.02574, posted 2 November 2026, accepted at the MOSS workshop at COLM 2026) tracked Ai2’s open OLMo 2 1B model across 13 training snapshots on grade-school maths. First-try accuracy rose from 58.0% to 61.3%, while a simple detector for planted arithmetic mistakes stayed flat; the only internal change the authors found was at the final answer. Novel Cognition checked the paper against its own tables and released code, re-ran its accuracy measurements on a MacBook Pro with the authors’ own prompt and answer checker, and added the one model the paper leaves out: the one from before training began. The full analysis is at rlvr.novcog.us.com.

This excerpt comes from the named source. Read the original for the full reporting.