This study examines Retrieval-Augmented Generation (RAG) in large language models (LLMs) and their significant application for undertaking systematic literature reviews (SLRs). RAG-based LLMs can potentially automate tasks like data extraction, summarization, and trend identification. However, while LLMs are exceptionally proficient in generating human-like text and interpreting complex linguistic nuances, their dependence on static, pre-trained knowledge can result in inaccuracies and hallucinations. RAG mitigates these limitations by integrating LLMs’ generative capabilities with the precision of real-time information retrieval. We review in detail the three key processes of the RAG framework—retrieval, augmentation, and generation. We then discuss applications of RAG-based LLMs to SLR automation and highlight future research topics, including integration of domain-specific LLMs, multimodal data processing and generation, and utilization of multiple retrieval sources. We propose a framework of RAG-based LLMs for automating SRLs, which covers four stages of SLR process: literature search, literature screening, data extraction, and information synthesis. Future research aims to optimize the interaction between LLM selection, training strategies, RAG techniques, and prompt engineering to implement the proposed framework, with particular emphasis on the retrieval of information from individual scientific papers and the integration of these data to produce outputs addressing various aspects such as current status, existing gaps, and emerging trends.

An important course in the computer science discipline is ‘Data Structures and Algorithms’ (DSA). The coursework lays emphasis on experiential learning for building students’ programming and algorithmic reasoning abilities. Teachers set up a repertoire of formative programming exercises to engage students with different programmatic scenarios to build their know-what, know-how and know-why competencies. Automated assessment tools can assist teachers in inspecting, marking, and grading of programming exercises and also support them in providing students with formative feedback in real-time. This article describes the design of a bespoke automarker that was integrated into the DSA coursework and therefore served as an instructional tool. Activity theory has provided the pedagogical lens to examine how the automarker-mediated instructional strategy enabled self-reflection and assisted students in their formative learning journey. Learner experiences gathered from 39 students enrolled in DSA course shows that the automarker facilitated practice-based learning to advance students know-what, know-why and know-how skills. This study contributes to both curricula and pedagogic practice by showcasing the integration of an automated assessment strategy with programming-related coursework to inform future teaching and assessment practice.

This study quantifies how prompting strategies interact with large language models (LLMs) to automate the screening stage of systematic literature reviews (SLRs). We evaluate six LLMs (GPT-4o, GPT-4o-mini, DeepSeek-Chat-V3, Gemini-2.5-Flash, Claude-3.5-Haiku, Llama-4-Maverick) under five prompt types (zero-shot, few-shot, chain-of-thought (CoT), CoT-few-shot, self-reflection) across relevance classification and six Level-2 tasks, using accuracy, precision, recall, and F1. Results show pronounced model-prompt interaction effects: CoT-few-shot yields the most reliable precision-recall balance; zero-shot maximizes recall for high-sensitivity passes; and self-reflection underperforms due to over-inclusivity and instability across models. GPT-4o and DeepSeek provide robust overall performance, while GPT-4o-mini performs competitively at a substantially lower dollar cost. A cost-performance analysis for relevance classification (per 1,000 abstracts) reveals large absolute differences among model-prompt pairings; GPT-4o-mini remains low-cost across prompts, and structured prompts (CoT/CoT-few-shot) on GPT-4o-mini offer attractive F1 at a small incremental cost. We recommend a staged workflow that (1) deploys low-cost models with structured prompts for first-pass screening and (2) escalates only borderline cases to higher-capacity models. These findings highlight LLMs' uneven but promising potential to automate literature screening. By systematically analyzing prompt-model interactions, we provide a comparative benchmark and practical guidance for task-adaptive LLM deployment.

This study quantifies how prompting strategies interact with large language models (LLMs) to automate the screening stage of systematic literature reviews (SLRs). We evaluate six LLMs (GPT-4o, GPT-4o-mini, DeepSeek-Chat-V3, Gemini-2.5-Flash, Claude-3.5-Haiku, and Llama-4-Maverick) under five prompt types (zero-shot, few-shot, chain-of-thought [CoT], CoT-few-shot, and self-reflection) across relevance classification and six Level-2 tasks, using accuracy, precision, recall, and F1. Results show pronounced model–prompt interaction effects within this SLR-automation corpus: zero-shot maximizes recall for high-sensitivity relevance screening; CoT-few-shot yields stronger precision and F1; and self-reflection underperforms due to over-inclusivity and instability across models. GPT-4o and DeepSeek provide robust overall performance, while GPT-4o-mini performs competitively at a substantially lower dollar cost. A cost-performance analysis for relevance classification (per 1,000 abstracts) reveals large absolute differences among model–prompt pairings; GPT-4o-Mini remains low-cost across prompts, and structured prompts (CoT/CoT-few-shot) on GPT-4o-Mini offer attractive F1 at a small incremental cost. The cost-performance analysis also suggests that future screening workflows could incorporate staged, cost-aware procedures: (1) using lower-cost, high-recall configurations for initial screening and (2) reserving higher-cost or more precision-oriented configurations for later triage or uncertain records. These findings highlight LLMs’ uneven but promising potential to support screening within corpora similar to the SLR-automation corpus examined in this study. Further validation is needed before generalising these results to broader systematic review screening tasks. By systematically analyzing prompt–model interactions, we provide a comparative benchmark and practical guidance for task-adaptive LLM deployment.