ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision? | alphaXiv

ZeroCoder introduces a label-free co-evolutionary framework for Large Language Models, significantly enhancing both code and test generation capabilities b

Submitted 28 Jun 2026 LF Lishui Fan MC Mouxiang Chen TZ Tingwei Zhu KL Kui LiuXin Xia SL Shanping Li ZL Zhongxin Liu Abstract Code generation is important in software engineering, and Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm to improve it through execution-based feedback. However, most RLVR pipelines rely on human-curated tests, making progress bottlenecked by scarce and costly supervision. Existing work tried to use self-generated tests to ground rewards, but the lack of discriminative tests constrains the effect due to the sub-optimal…

saved by

• Al-Ekram Elahee Hridoy

related reading

• [2501.01257] CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratingsarxiv.org
• CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationalphaxiv.org
• BigO(Bench) -- Can LLMs Generate Code with Controlled Time and Space Complexity?alphaxiv.org
• [2605.02421] AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMsarxiv.org
• Coding Models Are Doing Too Much | whnrehiew.github.io
• [2203.07814] Competition-Level Code Generation with AlphaCodearxiv.org
• [2604.22082] Removing Sandbagging in LLMs by Training with Weak Supervisionarxiv.org
• [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
• LiCoEval: Evaluating LLMs on License Compliance in Code Generationarxiv.org
• The Verification Horizon: No Silver Bullet for Coding Agent Rewardsarxiv.org
• Introducing FrontierCode | Cognitioncognition.ai
• [2506.13131] AlphaEvolve: A coding agent for scientific and algorithmic discoveryarxiv.org