Software Testing Verification and Reliability· 2026Q2
AgentTester: Improve Coverage in Automated Test Generation With Multi‐Agent as Optimizer
- 0citations
- Q2SCImago
- 2026year
Short summary
AgentTester, a multi-agent LLM framework using Chain-of-Thought reasoning, significantly improves automated test case generation by assigning subtasks to specialized agents, outperforming baselines in executable rate, coverage, readability, and convergence speed.
AI-generated from the title and abstract; the full text is not read.
Key points
- AgentTester utilizes a multi-agent LLM framework with Chain-of-Thought (CoT) reasoning for automated test case generation.
- Subtasks in the search process are assigned to specialized agents, replacing undirected randomness of traditional methods.
- AgentTester shows improved performance in executable rate, coverage, readability, and convergence speed compared to baselines.
- The framework validates the effectiveness of individual agents and the potential of LLMs in complex reasoning for software testing.
AI-generated from the title and abstract; the full text is not read.
Abstract
ABSTRACT Heuristic algorithms have been widely applied in search‐based software testing (SBST), playing a critical role in the automated generation of high‐coverage test cases. These algorithms often rely on random operations such as initialization, crossover and mutation to provide diverse individuals for search. However, it is possible to cause low‐quality solutions and a waste of resources due to their undirected randomness, which can be replaced by clear end‐to‐end reasoning. For large language models (LLMs) have demonstrated exceptional capabilities in handling simple reasoning tasks with the Chain‐of‐Thought (CoT) scheme, this paper introduces AgentTester, a multi‐agent framework of LLM, where subtasks in the search process are assigned to multiple agents applying CoT to efficiently generate high‐quality test cases. Experimental results show that AgentTester outperforms comparison baselines across benchmarks in generation with high executable rate, coverage, readability and convergence speed. Results validate the effectiveness of each agent and further underscore the potential of LLM in addressing complex reasoning tasks.
The authors' abstract, as published at the source. Software Testing Verification and Reliability, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Software
SoftwareComputer Science