aspg-31-4457-1791686943 20261011024903 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group International Journal of Advances in Applied Computational Intelligence IJAACI 2833-5600 2026 8 2 Safina Shokeen Department of Industrial Internet of Things, School of Engineering and Technology, Vivekananda Institute of Professional Studies–Technical Campus, Delhi 110034, India Vishal Srivastava Department of Industrial Internet of Things, School of Engineering and Technology, Vivekananda Institute of Professional Studies–Technical Campus, Delhi 110034, India Large language models now routinely produce metaheuristic optimisation code in response to natural-language prompts, yet the structural integrity of such generated implementations has received little systematic scrutiny. Syntactically valid code that misrepresents algorithmic logic or parameter semantics constitutes a form of hallucination specific to optimisation software — one that is difficult to detect without execution-level testing and that can produce catastrophic performance degradation without any visible error signal. This work introduces a five-category taxonomy of algorithmic hallucination covering parameter value hallucination, update-formula omission, boundaryhandling failure, reproducibility failure, and termination-logic error. A controlled audit is conducted by injecting each hallucination type into verified reference implementations of three widely used metaheuristics — particle swarm optimisation, differential evolution, and a genetic algorithm — and evaluating their behaviour across five standard continuous benchmark functions. Across twenty independent trials per condition, parameter hallucination and formula-omission errors produce best-fitness degradation exceeding 108-fold relative to the reference, while boundary-handling failures generate more than 4 000 out-of-bounds constraint violations per trial. Reproducibility failure inflates inter-trial variance by three to four orders of magnitude, and premature-termination errors induce a 100% trial failure rate. The results demonstrate that current LLM-generated metaheuristic code requires structured execution-level validation before deployment, and a practical audit protocol is proposed to support that process. Experimental artefacts, including all source code, generated data, and benchmark results, are released to support reproducible follow-on research. 2026 11 18 4457 https://creativecommons.org/licenses/by/4.0/ 10.54216/IJAACI.080202 https://www.americaspg.com/journal/31/article/4457 https://www.americaspg.com/storage/articles/manuscripts/01KY5VY3ADDKE330QE338AY12Y.pdf