The field of network protocol validation and software repair is experiencing significant advancements, driven by the integration of large language models (LLMs) and formal methods. Researchers are exploring innovative ways to leverage LLMs to improve the correctness and security of network protocols and software systems. One notable direction is the use of LLMs to generate formal specifications from natural language documentation, enabling the automated validation of protocol implementations. Another area of focus is the development of LLM-based repair agents that can effectively fix bugs in complex systems, such as the Linux kernel. These advancements have the potential to significantly improve the reliability and security of software systems. Notable papers in this area include: Validating Network Protocol Parsers with Traceable RFC Document Interpretation, which presents an effective solution for validating network protocol implementations using LLMs. CrashFixer: A crash resolution agent for the Linux kernel, which introduces the first LLM-based software repair agent applicable to Linux kernel bugs. OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification, which provides a new benchmark for evaluating LLMs in generating complete specification code for operating system kernel verification tasks.