SOURCE-LINKED INTELLIGENCE

Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for coding problems mainly comes from specific test cases, where high-quality test cases are often scarce since they should be both sound and discriminative. We thus turn to study the auto-generation of test cases using the learned model. We find this is naturally an adversarial RL problem: the model is expected to generate effective test cases as counterexamples, depending on the solver's current failure modes. We propose Test Cases Scaling (TCS),

Read original source ↗ Open in workspace

recordType

paper

region

Global