Correctness vs Efficiency: Behavior Control with Weight-Space Extrapolation in Code RL

arXiv:2605.28751 · cs.LG, cs.AI, cs.CL · Submitted 2026-05-27 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-05-27

Updated: 2026-11-09

Terminology

Sources

Related papers