SeGa detects 29 of 60 real business-logic bugs by generating tests from requirement-document scenarios, 22-25 more than four LLM-based baselines.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.SE 5roles
method 1polarities
use method 1representative citing papers
CAT improves line coverage by 18% and branch coverage by 22% over prior LLM test generation methods by adding call-chain and dependency context from static analysis to prompts.
TestGeneralizer generalizes an initial test into a set of executable tests covering more diverse scenarios, delivering +31.66% mutation-based and +23.08% LLM-assessed scenario coverage gains over ChatTester on 12 open-source Java projects.
By proving test suite coverage is monotone submodular and training LLMs with RL to maximize marginal gains, TestDecision improves branch coverage 38-52% and bug detection up to 95% over base models on ULT and LiveCodeBench.
IntentionTest generates project-specific tests from a validation-intention description by retrieving a similar existing test and editing it with an LLM and project-specific code facts.
citing papers explorer
-
Uncovering Business Logic Bugs via Semantics-Driven Unit Test Generation
SeGa detects 29 of 60 real business-logic bugs by generating tests from requirement-document scenarios, 22-25 more than four LLM-based baselines.
-
Call-Chain-Aware LLM-Based Test Generation for Java Projects
CAT improves line coverage by 18% and branch coverage by 22% over prior LLM test generation methods by adding call-chain and dependency context from static analysis to prompts.
-
Generalizing Test Cases for Comprehensive Test Scenario Coverage
TestGeneralizer generalizes an initial test into a set of executable tests covering more diverse scenarios, delivering +31.66% mutation-based and +23.08% LLM-assessed scenario coverage gains over ChatTester on 12 open-source Java projects.
-
TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning
By proving test suite coverage is monotone submodular and training LLMs with RL to maximize marginal gains, TestDecision improves branch coverage 38-52% and bug detection up to 95% over base models on ULT and LiveCodeBench.
-
Generating Project-Specific Test Cases with Requirement Validation Intention
IntentionTest generates project-specific tests from a validation-intention description by retrieving a similar existing test and editing it with an LLM and project-specific code facts.