Skip to main content
Search

# Negative-Only Policy Optimization

1 related articles

Subscribe to updates
  1. arXiv

    When verifiers can reject but not certify, NOPO learns only from failures and lifts average pass@16 above GRPO on code, logic and math

    When a verifier can reliably reject wrong answers but cannot reliably certify correct ones, standard reinforcement learning with verifiable rewards reinforces shortcuts that merely pass partial checks. NOPO treats verifier-positive samples as unlabeled candidates and updates the policy only by suppressing trusted negatives, scaling each update by the share of non-falsified responses in the same rollout group. On Qwen3-4B and Qwen3-8B, average pass@16 on code, logic and math benchmarks exceeds GRPO and other baselines, and the advantage persists under inference-time scaling to 512 samples and cross-benchmark transfer.

You’re all caught up