Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning.

Biometric data privacy is becoming a major concern for many organizations in the age of big data, particularly in the ICT sector, because it may be easily exploited in apps. Most apps utilize biometrics by accessing common application programming interfaces (APIs); hence, we aim to categorize their usage. The categorization based on behavior may be closely correlated with the sensitive processing of a user's biometric data, hence highlighting crucial biometric data privacy assessment concerns. We propose PABAU, Privacy Analysis of Biometric API Usage. PABAU learns semantic features of methods in biometric APIs and uses them to detect and categorize the usage of biometric API implementation in the software according to their privacy-related behaviors. This technique bridges the communication and background knowledge gap between technical and non-technical individuals in organizations by providing an automated method for both parties to acquire a rapid understanding of the essential behaviors of biometric API in apps, as well as future support to data protection officers (DPO) with legal documentation, such as conducting a Data Protection Impact Assessment (DPIA).

The sequence-to-sequence (seq2seq) model for neural machine translation has significantly improved the accuracy of language translation. There have been new efforts to use this seq2seq model for program language translation or program comparisons. In this work, we present the detailed steps of using a seq2seq model to translate CUDA programs to OpenCL programs, which both have very similar programming styles. Our work shows (i) a training input set generation method, (ii) pre/post processing, and (iii) a case study using Polybench-gpu-1.0, NVIDIA SDK, and Rodinia benchmarks.