MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning

TL;DR

MIST-RL introduces a reinforcement learning framework for incremental test suite generation that emphasizes utility over quantity, leading to more effective fault detection and improved code verification.

Contribution

It presents a novel mutation-based incremental testing approach optimized via reinforcement learning, outperforming existing methods in fault detection and verification efficiency.

Findings

Achieves +28.5% higher mutation score

Reduces test cases by 19.3%

Improves code reranking accuracy by 3.05%

Abstract

Large Language Models (LLMs) often fail to generate correct code on the first attempt, which requires using generated unit tests as verifiers to validate the solutions. Despite the success of recent verification methods, they remain constrained by a "scaling-by-quantity" paradigm. This brute-force approach suffers from a critical limitation: it yields diminishing returns in fault detection while causing severe test redundancy. To address this, we propose MIST-RL (Mutation-based Incremental Suite Testing via Reinforcement Learning), a framework that shifts the focus to "scaling-by-utility". We formulate test generation as a sequential decision process optimized via Group Relative Policy Optimization (GRPO). Specifically, we introduce a novel incremental mutation reward combined with dynamic penalties, which incentivizes the model to discover new faults while it suppresses functionally equivalent assertions. Experiments on HumanEval+ and MBPP+ demonstrate that MIST-RL outperforms state-of-the-art baselines. It achieves a +28.5% higher mutation score while reducing the number of test cases by 19.3%. Furthermore, we show that these compact, high-utility tests serve as superior verifiers, which improves downstream code reranking accuracy on HumanEval+ by 3.05% over the SOTA baseline with 10 candidate samples. The source code and data are provided in the supplementary material.