SeGa extracts business semantics from requirements to generate unit tests that detect 22-25 more real-world business logic bugs than prior LLM-based methods in industrial Go projects.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.SE 7roles
baseline 1polarities
baseline 1representative citing papers
PropGen automates property generation for Android app testing via LLM synthesis from guided exploration and feedback refinement, yielding 912 valid properties and 25 previously unknown bugs across 12 apps.
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.
AnyPoC introduces a multi-agent system for generating and validating PoC tests from LLM bug reports, producing 1.3x more valid PoCs, rejecting 9.8x more false positives, and discovering 122 new bugs across 12 major 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 retrieves a reusable test from the project and edits it with an LLM to match a supplied validation intention, yielding tests that kill 28.1-37.6% more mutants, share 16.9-23.9% more coverage, and produce 23.7-49.0% more passing tests than four baselines on 3,680 cases.
citing papers explorer
-
Uncovering Business Logic Bugs via Semantics-Driven Unit Test Generation
SeGa extracts business semantics from requirements to generate unit tests that detect 22-25 more real-world business logic bugs than prior LLM-based methods in industrial Go projects.
-
From Exploration to Specification: LLM-Based Property Generation for Mobile App Testing
PropGen automates property generation for Android app testing via LLM synthesis from guided exploration and feedback refinement, yielding 912 valid properties and 25 previously unknown bugs across 12 apps.
-
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.
-
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
AnyPoC introduces a multi-agent system for generating and validating PoC tests from LLM bug reports, producing 1.3x more valid PoCs, rejecting 9.8x more false positives, and discovering 122 new bugs across 12 major 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 retrieves a reusable test from the project and edits it with an LLM to match a supplied validation intention, yielding tests that kill 28.1-37.6% more mutants, share 16.9-23.9% more coverage, and produce 23.7-49.0% more passing tests than four baselines on 3,680 cases.