超越数值输入的边界值探索自适应策略生成
Adaptive Strategy Generation for Boundary Value Exploration Beyond Numeric Inputs
浏览论文内容
中文总结 AI 辅助
本文提出基于LLM的ABEX框架，以自适应策略生成替代手动设计变异算子，在含多类型输入的20个函数的黑盒测试中，其边界探索与故障揭示性能优于现有QD基线。
中文摘要 AI 辅助
软件行为常在输入区域的边界处突变，这类过渡区域易出现故障。边界值探索（BVE）通过搜索触发不同程序行为的相似输入对，实现边界发现的自动化。现有自动化BVE技术依赖针对每种输入类型甚至被测函数手动设计的变异算子，这使其仅能用于数值输入场景。本文提出ABEX，一种基于大语言模型（LLM）的智能体框架，用自适应策略生成替代算子工程：专用LLM智能体在执行反馈与质量多样性（QD）存档的引导下，提出、选择并执行边界探索策略。由于策略以自然语言表述，可编码类型级与函数特定知识，有效策略还可存储复用。我们在黑盒场景下对20个含数值、字符串、数组及混合输入的函数评估ABEX：在数值函数上，ABEX在11个函数中的10个上优于现有最优QD方法，平均QD分数高11.7倍；在非数值函数上，作为自动化黑盒BVE中首次处理的场景，ABEX为所有被测对象发现了与领域对齐的边界行为。变异测试显示，所发现边界具备故障揭示能力：在测试套件规模相同时，ABEX的平均变异分数达86.2%，而QD基线仅为61.9%，且能杀死9倍于基线的难检测顽固变异体。消融研究表明，自适应策略生成是上述性能提升的主要驱动因素。
英文摘要
Software behavior often changes abruptly at boundaries between input regions, and these transitions are known to be fault-prone. Boundary Value Exploration (BVE) automates boundary discovery by searching for pairs of similar inputs that nevertheless trigger different program behaviors. Existing automated BVE techniques rely on mutation operators hand-engineered for each input type, or even for each function under test, which has confined their use to numeric inputs. We present ABEX, an agentic LLM-based framework that replaces operator engineering with adaptive strategy generation: specialized LLM agents propose, select, and execute boundary-exploration strategies, guided by execution feedback and a quality-diversity (QD) archive. Because strategies are expressed in natural language, they can encode both type-level and function-specific knowledge, and effective strategies can even be stored and reused. We evaluate ABEX in a black-box setting on 20 functions with numeric, string, array, and mixed inputs. On numeric functions, ABEX outperforms a state-of-the-art QD method on 10 of 11 functions, with average QD-scores 11.7x higher. On non-numeric functions, addressed here for the first time in automated black-box BVE, ABEX discovers domain-aligned boundary behaviors for all subjects. Mutation testing shows the discovered boundaries are fault-revealing: with equally sized test suites, ABEX reaches an average mutation score of 86.2% versus 61.9% for the QD baseline, and kills nine times as many hard-to-detect stubborn mutants. An ablation study identifies adaptive strategy generation as the primary driver of these gains.
