← Back to all news
arXiv Machine Learning By Jiacheng Xu, Feng Chen, Xiuneng Xu, Bo An

Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation

Read the original on arXiv Machine Learning →

The paper introduces probe-driven test-time reinforcement learning (TTRL) for code generation, using probe inputs derived from problem statements to evaluate candidate programs and define a Probe Consensus Reward (PCR). To address PCR’s unreliability and prevent reward hacking, the authors propose Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which applies rank masking and an entropy ceiling to produce conservative policy updates. Experiments on coding benchmarks show that ERPO significantly improves pass@1 and pass@k metrics in both in-domain adaptation and zero-shot transfer scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 24

AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning

arXiv:2508.14313v4 Announce Type: replace-cross Abstract: Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or sea...

By Can Jin, Yang Zhou, Qixin Zhang, Hongwu Peng, Di Zhang, Zihan Dong, Marco Pavone, Ligong Han, Zhang-Wei Hong, Tong Che, Dimitris N. Metaxas
llmsreinforcement-learningbenchmarkssafety
More like this →
Hugging Face Trending Papers
Aug 27

TTPO: Test-Time Policy Optimization

The paper introduces Test‑Time Policy Optimization (TTPO), a method that enables large language models to improve mathematical reasoning during inference without relying on ground‑truth labels. TTPO uses majority‑vote pseudo‑labels to guide an asymmetric objective: agreeing rollouts are distilled via On‑Policy Self‑Distillation, while disagreeing rollouts are penalized with Grouped Reinforcement Learning, with token‑level selection refining both branches. Experiments show that TTPO matches label‑supervised OPSD on five benchmarks, boosts Qwen3‑1.7B from 38.0 % to 45.2 % in test‑time training, and achieves significant gains without explicit reasoning steps, demonstrating strong cross‑task generalization.

llmsreinforcement-learningefficiencybenchmarks
More like this →