Automated Test Generation

Follow this topic Ask about this topic

Automated test generation studies how to create inputs and checks that reveal defects in software, APIs, hardware, and simulated systems. Methods include search-based testing and fuzzing, symbolic and constraint-based generation, property-based and metamorphic testing, and increasingly LLM agents guided by execution, coverage, or mutation feedback. Evaluation commonly measures coverage, mutation scores, bug detection, and whether tests distinguish correct behavior from faulty implementations. A central challenge is that executable tests and high coverage do not guarantee semantic correctness: weak oracles, incomplete specifications, and prompts based on buggy code can produce tests that miss faults or reinforce them.

Latest papers

133 papers20 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Enhancing LLM-Based Test Generation by Eliminating Covered Code
Feb 25, 2026WeiZhe Xu, Mengyu Liu, Fanxin KongAutomated Test Generation LLM Code Generation
University of Notre Dame, Notre Dame, IN, USA · Washington State University, Richland, WA, USA
CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
Feb 23, 2026Jingwei Shi, Xinxiang Yin, Jing Huang +2Automated Test Generation Adversarial Scenario Generation
Shanghai University of Finance and Economics · Northwestern Polytechnical University · Meituan +1
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
Feb 18, 2026Hejia Zhang, Zhongming Yu, Chia-Tung Ho +3LLM Agent Training Automated Test Generation
University of California San Diego, USA · NVIDIA · Agentrys
SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation
Feb 18, 2026Jaid Monwar Chowdhury, Chi-An Fu, Reyhaneh JabbarvandAutomated Test Generation Execution-Guided Code Generation
Bangladesh University of Engineering and Technology, Dhaka, Bangladesh · National Taiwan University, Taipei, Taiwan · University of Illinois at Urbana-Champaign, Champaign, IL, USA
Latent Regularization in Generative Test Input Generation
Feb 17, 2026Giorgi Merabishvili, Oliver Weißl, Andrea StoccoAutomated Test Generation Latent Space Optimization
North Carolina State University USA · Technical University of Munich & fortiss GmbH Germany
HyperNet-Adaptation for Diffusion-Based Test Case Generation
Jan 21, 2026Oliver Weißl, Vincenzo Riccio, Severin Kacianka +1Hypernetworks Automated Test Generation
Technical University of Munich, Germany · University of Udine, Italy · Independent Researcher, Germany +1
SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories
Jan 20, 2026Aditya Bharat Soni, Rajat Ghosh, Vaishnavi Bhargava +2LLM Post-Training Automated Test Generation
Carnegie Mellon University · Nutanix · Stanford University
MASTEST: A LLM-Based Multi-Agent System For Testing RESTful APIs
Nov 22, 2025Xiaoke Han, Hong ZhuMulti-Agent LLM Systems Automated Software Testing
School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK
Towards Functional Correctness of Code Models with Selective Generation
May 19, 2025Jaewoo Jeong, Taesoo Kim, Sangdon ParkCode Generation Code Generation Evaluation
CSE, POSTECH · SCS&SCP GaTech · Microsoft +1
Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing
Mar 11, 2025Lev Sorokin, Matteo Biagiola, Andrea StoccoAutomated Software Testing Autonomous Driving Simulation
Technical University of Munich, Munich, Germany. · University of St. Gallen and Universit`a della Svizzera italiana, St. Gallen / Lugano, Switzerland. · fortiss GmbH, Munich, Germany.
Evaluating LLM-Based Regression Test Generation
Jan 19, 2025Jing Liu, Seongmin Lee, Eleonora Losiouk +1Automated Test Generation LLM Code Generation
MPI-SP, Germany · University of California at Los Angeles, USA · University of Padua, Italy
Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models
Dec 10, 2024Chang-Jin Li, Jiyuan Zhang, Yun Tang +1Psychometric Validation Automated Test Generation
Faculty of Psychology, Beijing Normal University, Beijing, 100875, China · School of Psychology, Central China Normal University, Wuhan, Hubei, 430079, China · Key Laboratory of Adolescent Cyberpsychology and Behavior, Ministry of Education, Wuhan, Hubei, 430079, China +1
Requirement-Based Testing: Enhancing Reinforcement Learning with Game Theory
Jul 26, 2024Ocan Sankur, Thierry Jéron, Nicolas Markey +2Automated Software Testing Automated Test Generation
DEVINE · MERCE-France · Mitsubishi Electric Corporation, Tokyo, Japan

Feb 25, 2026J/K move · Enter open · S save

Enhancing LLM-Based Test Generation by Eliminating Covered Code

WeiZhe Xu, Mengyu Liu, Fanxin Kong

University of Notre Dame, Notre Dame, IN, USA · Washington State University, Richland, WA, USA

Automated Test Generation LLM Code Generation

Open paper AskPDF arXiv

Automated test generation is essential for software quality assurance, with coverage rate serving as a key metric to ensure thorough testing. Recent advancements in Large Language Models (LLMs) have shown promise in improving test generation, particularly in achieving higher coverage. However, while existing LLM-based test generation solutions perform well on small, isolated code snippets, they struggle when applied to complex methods under test. To address these issues, we propose a scalable LLM-based unit test generation method. Our approach consists of two key steps. The first step is context information retrieval, which uses both LLMs and static analysis to gather relevant contextual information associated with the complex methods under test. The second step, iterative test generation with code elimination, repeatedly generates unit tests for the code slice, tracks the achieved coverage, and selectively removes code segments that have already been covered. This process simplifies the testing task and mitigates issues arising from token limits or reduced reasoning effectiveness associated with excessively long contexts. Through comprehensive evaluations on open-source projects, our approach outperforms state-of-the-art LLM-based and search-based methods, demonstrating its effectiveness in achieving high coverage on complex methods.