Understanding the Effect of Agentic Iteration on LLM-Based Unit Test Generation: A Comparison with Human-Written Tests Using Mutation Testing
Recent work argues that multi-agent LLM frameworks generate better unit tests than a single well-crafted prompt by iteratively refining coverage and cross-checking oracles. We test this claim directly on a 25-class Java system, comparing CANDOR, a multi-agent framework with JaCoCodriven coverage feedback and panel-base...