The field of natural language processing is witnessing significant advancements in prompt optimization and large language models. Researchers are exploring new methods to improve the performance of large language models, including the use of reinforcement learning, meta-learning, and human feedback. One of the key challenges in prompt optimization is the need for large amounts of human-annotated data, which can be time-consuming and expensive to obtain. To address this, researchers are developing semi-automated frameworks that can generate instructions in a task-agnostic manner, reducing the need for human intervention. Another area of focus is the development of models that can generalize across different tasks and domains, enabling rapid adaptation to new tasks with minimal optimization. Noteworthy papers in this area include: REFINE-AF, which proposes a task-agnostic framework to align language models via self-generated instructions using reinforcement learning from automated feedback. PLHF, which presents a few-shot prompt optimization framework inspired by the well-known RLHF technique, requiring only a single round of human feedback to complete the entire prompt optimization process. Rethinking Prompt Optimizers, which introduces a merit-guided, lightweight, and locally deployable prompt optimizer trained on a preference dataset built from merit-aligned prompts generated by a lightweight LLM.