SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by surface form and therefore do not directly provide a usable training signal. To make TTRL applicable to code generation, we propose probe-driven TTRL, which constructs output-free probe inputs from the problem statement, executes candidate programs on these probes, and defines a Probe Consensus Reward (PCR) from the resulting behavioral agreement. PCR provide

Read original source ↗ Open in workspace

recordType

paper

region

Global