Jul 2026· International Conference Computing Methodologies and Communication· pp. 1610-1616· 0 citations· 17 references
Abstract
Prompt engineering is now a significant aspect of large language models (LLMs) to make them as effective in applications like conversational agents, educational assistants, automated code-generating systems, and content generation systems. Nonetheless, urgent design is frequently done in informal and solitary fashion devoid of systematic processes of collective enhancement, quality evaluation, or evolutionary monitoring. This paper suggests NeuroPrompt, an open-source prompt engineering system, which combines version tracking with evolution, directed acyclic graph (DAG) based lineage modeling, and community-based quality assessment. Users can create prompts, fork better prompts, and assess the performance of prompts with a multi-rater consensus system to assess the prompts based on clarity, creativity, and usefulness. The forking is directed by a utility-based decision model that ensures that unnecessary prompt duplication is avoided, and the effectiveness of optimization is enhanced. Experimental analysis reveals that collaborative prompt evolution is more effective in prompt quality and the overall accuracy of prompt generation in providing relevant and useful responses to tasks is 96.3% in comparison against baseline prompt design methods which has a score of about 88-91. There are also the results of the improved consensus reliability and lesser variance of ratings among the community evaluators. The suggested system will change timely engineering into a transparent and organized evolutionary process allowing sharing of knowledge systematically and optimizing prompt through collaborative optimization to large-scale AI initiatives.
Large Language Models (LLMs) have rapidly become central components of cognitive computing systems and AI-assisted knowledge work. However, the effectiveness of LLM-generated outputs depends not only on the model’s capabilities but also on the structure of the prompts used to guide them. This study investigates how structured prompting techniques influence perceived output usefulness in business-oriented tasks. First, we conduct a systematic literature review following PRISMA guidelines to identify, classify, and synthesize existing prompt enhancement strategies. The review leads to the development of a taxonomy distinguishing task-alignment techniques (e.g., one-shot and few-shot prompting) from reasoning-transparency techniques (e.g., Chain-of-Thought prompting). Building on this taxonomy, we design a controlled experimental study in which knowledge workers evaluate LLM-generated outputs across analytical and summarization tasks. Using linear mixed-effects modeling, we assess the impact of prompting techniques and the moderating role of Generative AI usage frequency. Results indicate that structured prompting significantly increases perceived usefulness compared to baseline approaches, with the combination of example-based conditioning and explicit reasoning scaffolding yielding the highest evaluations. The moderating effect of usage frequency is not statistically significant, suggesting that the benefits of structured prompt design are robust across different experience levels. These findings position prompt structure as a practical cognitive interface mechanism and provide evidence-based guidelines for enhancing human–AI interaction in cognitive computing environments.
A. Cantini, Andrea De Mauro· Big Data and Cognitive Compu...· 0 citations
RLMOpt is introduced, a prompt optimizer that makes the search policy itself language-model-driven through a recursive language model (RLM), which operates over a tool-based environment, inspecting task information, analyzing failures, generating candidates, allocating evaluation budget, and deciding when to stop.
Pilot test results indicate adequate average response times, thematic and temporal diversity of authors and robust data structuring, confirming its viability as an applicable prototype and advancing the integration of generative AI into library services.
Manuel Blázquez-Ochando, J. Prieto-Gutiérrez, María-Antonia Ovalle-Perandones· Library hi tech· 0 citations
An empirical study of configuration prompt files in Cursor, a widely used AI-assisted code editor, shows that .cursorrules files emerged rapidly from mid-2024 and shows that there is a continuity of themes and topics between the now-legacy .cursorrules files and the current standard .mdc files.
Shuang Sun, Jafar Akhoundali, Arina Kudriavtseva et al.· Proceedings of the 21st Inte...· 1 citation· ⚡1
Effective use of Large Language Models (LLMs) depends heavily on the quality of the prompt supplied to them, yet most users lack familiarity with prompt engineering principles such as role, context, task, constraints, tone and output format, and consequently receive vague or off-target responses. Existing prompt-generation tools compound this problem: they focus on producing a response rather than helping the user construct a better instruction, and they are almost universally built around cloud AI APIs, introducing latency, recurring cost, data-privacy exposure and a hard dependency on connectivity. This paper presents the Smart Prompt Analyzer and Recommendation System, a Flask-based web platform that generates, analyzes and optimizes prompts using a completely self-hosted Large Language Model served through Ollama with the Qwen2.5:3B-Instruct model. The system decomposes a prompt into its constituent engineering elements through a rule-based Prompt DNA Analysis module, scores prompt quality, and produces intelligent recommendations to improve clarity, context and completeness before the prompt is ever submitted for generation. A modular architecture — comprising a web-based user interface, a Flask application server, a Prompt Analyzer, an Edge Cache and the Ollama service — keeps the system responsive and operational even when the underlying AI model is temporarily unavailable, since the rule-based analyzer transparently takes over as a fallback. Functional, integration, performance and user-acceptance testing across fifteen test cases confirmed correct end-to-end operation of prompt generation, Prompt DNA analysis and streamed content generation, with all issues identified during the first testing pass resolved prior to final validation. The system demonstrates that pairing local LLM inference with structured prompt-quality evaluation can make prompt engineering accessible to users with no prior background in the discipline, while eliminating the cost, latency and privacy concerns associated with cloud-hosted alternatives.
Bhoomika B, Nagamani H M, T. Vasudev· International Journal of Res...· 0 citations
ReASearch is presented, a unified framework for reasoning-driven optimization in which the agent autonomously decides what to evaluate, how to diagnose failures, which edits to make, and when to verify or restart.