Zeroing neural networks (ZNNs) play a crucial role in efficiently solving time-varying problems. Recently, ZNNs are integrated with many advanced control theories with a certain convergence time to enhance their performance. On account of the convergence time of the prescribed-time convergence is precise, it is of great significance to investigate ZNN with prescribed-time convergence. In addition, delay is unavoidable in circuit implementation, not only impacting the prescribed-time convergence but also inducing instability and oscillation in ZNN. To evaluate the effectiveness of prescribed-time ZNN under delay environment, prescribed-time delayed zeroing neural network (PTDZNN) is proposed for solving time-varying equations in this article. It is concluded that PTDZNN can obtain the correct real-time solution in prescribed time and the convergence time of PTDZNN is independent of initial conditions. Furthermore, PTDZNN exhibits notable tolerance to delay and distinguishes itself from existing delayed zeroing neural networks by its independence from linear matrix inequality (LMI). Moreover, the LMI-independent stability proof of ZNN under delay environment is also proved. Numerical simulations are presented to demonstrate the prescribed-time convergence and delay tolerance of PTDZNN. Ultimately, PTDZNN is successfully applied in dynamic positioning algorithms and image fusion problems. Notably, PTDZNN stands out as the first ZNN to incorporate both prescribed-time convergence and delay.

Fault localization (FL) targets identifying bug locations within a software system, which can enhance debugging efficiency and improve software quality. Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are limited in flexibility. They rely on bug-triggering test cases to perform FL and cannot make use of other available bug-related information, e.g., bug reports. Second, they are built upon proprietary LLMs, which are, although powerful, confronted with risks in data privacy. To address these limitations, we propose a novel LLM-based FL framework named FlexFL, which can flexibly leverage different types of bug-related information and effectively work with open-source LLMs. FlexFL is composed of two stages. In the first stage, FlexFL reduces the search space of buggy code using state-of-the-art FL techniques of different families and provides a candidate list of bug-related methods. In the second stage, FlexFL leverages LLMs to delve deeper to double-check the code snippets of methods suggested by the first stage and refine fault localization results. In each stage, FlexFL constructs agents based on open-source LLMs, which share the same pipeline that does not postulate any type of bug-related information and can interact with function calls without the out-of-the-box capability. Extensive experimental results on Defects4J demonstrate that FlexFL outperforms the baselines and can work with different open-source LLMs. Specifically, FlexFL with a lightweight open-source LLM Llama3-8B can locate 42 and 63 more bugs than two state-of-the-art LLM-based FL approaches AutoFL and AgentFL that both use GPT-3.5. In addition, FlexFL can localize 93 bugs that cannot be localized by non-LLM-based FL techniques at the top 1. Furthermore, to mitigate potential data contamination, we conduct experiments on a dataset which Llama3-8B has not seen before, and the evaluation results show that FlexFL can also achieve good performance.

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this comprehensive context comes at a cost: while it enhances model performance, it also increases inference latency. This balance between improved accuracy and computational efficiency poses a significant challenge in real-world applications. We present RepoGenix, a solution that enhances repository-level code completion without increased latency. RepoGenix combines analogous context and relevant context, using Context-Aware Selection technology to efficiently compress these contexts into limited-size prompts. Our experiments on CrossCodeEval demonstrate that RepoGenix not only achieves a substantial 48.41% reduction in inference time, but also yields improvement in performance compared to baseline methods. We have successfully implemented and tested RepoGenix within AntGroup's development environments. This approach is being extended to multiple programming languages and will be open-sourced, aiming to enhance code completion efficiency for the broader developer community.