nancui0000 / adaptive-mogrpoView on GitHub
Adaptive Weight Scheduling for Multi-Objective GRPO in Code Generation. Fixed multi-objective rewards cause reward hacking (short but broken code). Our curriculum approach—correctness first, then gradually adding efficiency/brevity—preserves 81.7% HumanEval while generating 11% shorter code.
49Apr 14, 2026Updated 2 weeks ago

Alternatives and similar repositories for adaptive-mogrpo

Users that are interested in adaptive-mogrpo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?