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

arXiv: https://arxiv.org/abs/2609.21208 · HTML: https://mlsanity.com/paper/2609.21208/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024)
- [S*: Test Time Scaling for Code Generation](https://mlsanity.com/paper/2502.14382/) (2025)
- [Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency](https://mlsanity.com/paper/2309.17272/) (2023)
- [SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning](https://mlsanity.com/paper/2504.19162/) (2025)
- [DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO](https://mlsanity.com/paper/2512.21514/) (2025)
- [Propose, Solve, Verify: Self-Play Through Formal Verification](https://mlsanity.com/paper/2512.18160/) (2025)

## Abstract (arXiv)

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 mutual information between its pass/fail vector and a graded, ground-truth-anchored correctness signal y [0, 1] m, gated by the sign of their covariance so that only positively discriminative tests receive reward. Second, a three-stage diversity-aware selection step prunes a candidate pool to a behaviourally non-redundant suite (invalidity, input-string, execution-profile filtering), raising the effective sample size of the IG estimator at fixed execution budget. On five benchmarks (LiveBench, MBPP, LiveCodeBench, CodeContests, Code-Forces), CoVer raises one-shot pass@1 by +5.8 points at 7B and +7.1 points at 14B over the Qwen2.5-Instruct backbone, and achieves the highest macro-average among all compared methods at both scales. As a drop-in backbone inside the CodeT ranking pipeline, CoVer-7B adds +3.5 points, demonstrating the dual benefit of co-training for both generation and selection.