SOURCE-LINKED INTELLIGENCE

Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but they suffer from two coupled pathologies: permissiveness collapse, where pass-rate rewards are maximised by trivial, non-discriminative tests, and concentration bias, where i.i.d. sampled tests cluster on modal inputs and inflate estimator variance. We introduce CoVer (Co-trained Coder and Verifier), a single-policy GRPO framework that addresses both failure modes. First, an information-gain (IG) reward scores each self-generated test by the mut

Read original source ↗ Open in workspace

recordType

paper

region

Global