Call-Chain-Aware LLM-Based Test Generation for Java Projects

arXiv:2604.22046 · cs.SE, cs.AI · Submitted 2026-04-23 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-04-23

Updated: 2026-10-11

Code: https://github.com/binance/binance-connector-java

Project page: https://qwenlm.github.io/qwen-code-docs/en/users/overview

Terminology

• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• LLM Test Generation via Iterative Hybrid Program Analysis
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• Mutation-Guided Unit Test Generation with a Large Language Model
• PALM: Path-aware LLM-based Test Generation with Comprehension
• Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation
• TestBench: Evaluating Class-Level Test Case Generation Capability of Large Language Models

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties