Large Language Model (LLM) Agents leverage the advanced reasoning capabilities of LLMs in real-world applications. To interface with an environment, these agents often rely on tools, such as web search or database APIs. As the agent provides the LLM with tool documentation along the user query, the completeness and correctness of this documentation is critical. However, tool documentation is often over-, under-, or ill-specified, impeding the agent's accuracy. Standard software testing approaches struggle to identify these errors as they are expressed in natural language. Thus, despite its importance, there currently exists no automated method to test the tool documentation for agents. To address this issue, we present ToolFuzz, the first method for automated testing of tool documentations. ToolFuzz is designed to discover two types of errors: (1) user queries leading to tool runtime errors and (2) user queries that lead to incorrect agent responses. ToolFuzz can generate a large and diverse set of natural inputs, effectively finding tool description errors at a low false positive rate. Further, we present two straightforward prompt-engineering approaches. We evaluate all three tool testing approaches on 32 common LangChain tools and 35 newly created custom tools and 2 novel benchmarks to further strengthen the assessment. We find that many publicly available tools suffer from underspecification. Specifically, we show that ToolFuzz identifies 20x more erroneous inputs compared to the prompt-engineering approaches, making it a key component for building reliable AI agents.
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
University of Science and Technology of China（中国科学技术大学）；QI-ANXIN Technology Research Institute（奇安信技术研究院）；Chaitin Future Technology Co., Ltd（观想未来科技有限公司）
The automation of functional testing in software has allowed developers to continuously check for negative impacts on functionality throughout the iterative phases of development. This is not the case for User eXperience (UX), which has hitherto relied almost exclusively on testing with real users. User testing is a slow endeavour that can become a bottleneck for development of interactive systems. To address this problem, we here propose an agent based approach for automatic UX testing. We develop agents with basic problem solving skills and a core affect model, allowing us to model an artifi…
TestLab: An Intelligent Automated Software Testing Framework
Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development (GECAD)（高级创新与发展智能工程与计算研究组（GECAD））；Porto School of Engineering (ISEP)（波尔图工程学院（ISEP））
本文提出智能自动化软件测试框架 TestLab，利用 AI 集成三类模块，从不同视角发现漏洞并基于源代码分析自动生成测试用例，以支持多层级持续测试。
Graz University of Technology（格拉茨工业大学）；Siemens Energy AG（西门子能源股份公司）；University of Sevilla（塞维利亚大学）
Variability models (e.g., feature models) are a common way for the representation of variabilities and commonalities of software artifacts. Such models can be translated to a logical representation and thus allow different operations for quality assurance and other types of model property analysis. Specifically, complex and often large-scale feature models can become faulty, i.e., do not represent the expected variability properties of the underlying software artifact. In this paper, we introduce DirectDebug which is a direct diagnosis approach to the automated testing and debugging of variabi…
The last decade has seen tremendous progress in AI technology and applications. With such widespread adoption, ensuring the reliability of the AI models is crucial. In past, we took the first step of creating a testing framework called AITEST for metamorphic properties such as fairness, robustness properties for tabular, time-series, and text classification models. In this paper, we extend the capability of the AITEST tool to include the testing techniques for Image and Speech-to-text models along with interpretability testing for tabular models. These novel extensions make AITEST a comprehens…
Ongoing progress in computational intelligence (CI) has led to an increased desire to apply CI techniques for the purpose of improving software engineering processes, particularly software testing. Existing state-of-the-art automated software testing techniques focus on utilising search algorithms to discover input values that achieve high execution path coverage. These algorithms are trained on the same code that they intend to test, requiring instrumentation and lengthy search times to test each software component. This paper outlines a novel genetic programming framework, where the evolved …
Columbia University（哥伦比亚大学）；Alibaba-NTU Joint Research Institute（阿里巴巴-南洋理工大学联合研究所）；Nanyang Technological University（南洋理工大学）；Universidade Federal Fluminense（弗卢米嫩塞联邦大学）
Automated Driving Systems (ADSs) have seen rapid progress in recent years. To ensure the safety and reliability of these systems, extensive testings are being conducted before their future mass deployment. Testing the system on the road is the closest to real-world and desirable approach, but it is incredibly costly. Also, it is infeasible to cover rare corner cases using such real-world testing. Thus, a popular alternative is to evaluate an ADS's performance in some well-designed challenging scenarios, a.k.a. scenario-based testing. High-fidelity simulators have been widely used in this setti…
Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）；Xbox Studios Quality（Xbox工作室质量部门）
Deep reinforcement learning (DRL) has attracted much attention in automated game testing. Early attempts rely on game internal information for game space exploration, thus requiring deep integration with games, which is inconvenient for practical applications. In this work, we propose using only screenshots/pixels as input for automated game testing and build a general game testing agent, Inspector, that can be easily applied to different games without deep integration with games. In addition to covering all game space for testing, our agent tries to take human-like behaviors to interact with …
General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-learning mechanism to the game testing framework. With DRL, the framework is capable of exploring and/or exploiting the game mechanics based on a user-defined, reinforcing reward signal. As a result, test coverage is increased and unintended game play mechanics, exploits and bugs are discovered in a multitude of game types. In this paper, we show that DRL can be used to increase te…
University of Alcalá（阿尔卡拉大学）；Joint Research Centre, European Commission（欧盟委员会联合研究中心）
Conventional vehicles are certified through classical approaches, where different physical certification tests are set up on test tracks to assess required safety levels. These approaches are well suited for vehicles with limited complexity and limited interactions with other entities as last-second resources. However, these approaches do not allow to evaluate safety with real behaviors for critical and edge cases, nor to evaluate the ability to anticipate them in the mid or long term. This is particularly relevant for automated and autonomous driving functions that make use of advanced predic…
University of Technology Sydney（悉尼科技大学）；Defence Science and Technology Group（国防科技集团）
Penetration testing the organised attack of a computer system in order to test existing defences has been used extensively to evaluate network security. This is a time consuming process and requires in-depth knowledge for the establishment of a strategy that resembles a real cyber-attack. This paper presents a novel deep reinforcement learning architecture with hierarchically structured agents called HA-DRL, which employs an algebraic action decomposition strategy to address the large discrete action space of an autonomous penetration testing simulator where the number of actions is exponentia…
