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

• URL: http://arxiv.org/abs/2604.07864v1
• Date: Thu, 09 Apr 2026 06:24:54 GMT
• Title: ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm to improve it through execution-based feedback.<n>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 performance of the model on test generation.<n>We present ZeroCoder, a fully label-free co-evolutionary framework that jointly trains a Coder and a Tester using execution feedback from self-generated code-test interactions.
• Score: 13.984583399745157
• License: http://creativecommons.org/licenses/by/4.0/
• 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 performance of the model on test generation. We aim to improve code generation without ground-truth supervision by co-evolving code and test generation, so that their interactions yield progressively more informative supervision. To this end, we present ZeroCoder, a fully label-free co-evolutionary framework that jointly trains a Coder and a Tester using execution feedback from self-generated code-test interactions. For each problem, ZeroCoder executes sampled solutions against sampled tests to form a passing matrix, identifies a consensus subset of likely-correct solutions and consistent tests via a pluggable selection algorithm, and derives role-specific rewards. To ensure reward quality, ZeroCoder filters low-information instances via rank-based pre-filtering and trains the Tester with a curriculum balancing validity and mutation-driven discriminativeness. We further identify selector drift, the progressive miscalibration of fixed selection rules during co-evolution, and introduce DyB4, a Bayesian selector that uses as few as 10 labeled instances to recalibrate its priors dynamically. Across three models and six benchmarks, ZeroCoder consistently improves code generation and test generation. In the fully label-free setting, it improves code generation by up to 14.5% over the base model on Qwen2.5-Coder-7B-Instruct. With DyB4, the gain reaches 21.6%, while test generation improves by 24.3%, approaching oracle-supervised performance.

Related papers

• Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping [25.919848220574803]
  RobustTests is a framework featuring a faulty-code-driven test case synthesis strategy.<n>It captures latent logical discrepancies and employs validator agents to filter invalid or redundant test cases.<n>We show that RL fine-tuning of Qwen3-32B via RobustTests achieves a 3% absolute gain on LiveCodeBench.
  arXiv  Detail & Related papers  (2026-08-25T07:00:08Z)
• MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation [9.901505812242652]
  We propose a closed-loop Test-Driven Development (TDD) framework based on the mutual reinforcement of code quality and case quality.<n>MineValiCoder significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-24T16:39:06Z)
• Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning [54.95476453942411]
  Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates.<n>Recent self-play methods unify code and test generation in a single model.<n>Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests.
  arXiv  Detail & Related papers  (2026-03-16T17:58:13Z)
• Scaling Agentic Verifier for Competitive Coding [66.11758166379092]
  Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt.<n>Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling.<n>We propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs.
  arXiv  Detail & Related papers  (2026-02-04T06:30:40Z)
• CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment [98.87395842351627]
  Large Language Models (LLMs) excel at code generation by learning from vast code corpora.<n>A fundamental semantic gap remains between their training on textual patterns and the goal of functional correctness.<n>We propose CodeRL+, a novel approach that integrates execution semantics alignment into the RLVR training pipeline for code generation.
  arXiv  Detail & Related papers  (2025-10-21T09:48:06Z)
• ATGen: Adversarial Reinforcement Learning for Test Case Generation [78.48498301767079]
  Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs.<n>Existing test generation methods rely on static datasets.<n>We introduce ATGen, a framework that trains a test case generator via adversarial reinforcement learning.
  arXiv  Detail & Related papers  (2025-10-16T12:49:25Z)
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning [48.66688117533318]
  We propose CURE, a novel reinforcement learning framework with a dedicated reward design.<n>CURE co-evolves coding and unit test generation capabilities based on their interaction outcomes.<n>We find that our model can serve as an effective reward model for reinforcement learning on base models.
  arXiv  Detail & Related papers  (2025-06-03T17:58:42Z)
• Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation [69.62857948698436]
  Recent advances in large language models (LLMs) have improved their performance on coding benchmarks.<n>However, improvement is plateauing due to the exhaustion of readily available high-quality data.<n>We propose Sol-Ver, a self-play solver-verifier framework that jointly improves a single model's code and test generation capacity.
  arXiv  Detail & Related papers  (2025-02-20T18:32:19Z)
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [10.730852617039451]
  We investigate the capability of LLM-based Code Agents to formalize user issues into test cases.<n>We propose a novel benchmark based on popular GitHub repositories, containing real-world issues, ground-truth bug-fixes, and golden tests.<n>We find that LLMs generally perform surprisingly well at generating relevant test cases, with Code Agents designed for code repair exceeding the performance of systems designed for test generation.
  arXiv  Detail & Related papers  (2024-06-18T14:54:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.