Citation :

Shreyansh Gupta, Shlok Dave, Dr. Vishal Shrivastava, Dr. Akhil Pandey, 2026. "A Survey of Prompt Engineering Techniques for Large Language Models: A Comparative Summary" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 4: 16-24.

Abstract :

Prompt engineering has emerged as the primary interface through which practitioners steer the behaviour of large language models (LLMs) without updating any model weights. Since the introduction of few-shot in-context learning, a wide family of prompting strategies has been proposed, ranging from simple zero-shot instructions to elaborate reasoning frameworks and agentic, tool-using prompts. This paper presents a comparative survey of the major prompt engineering techniques reported in the literature between 2020 and 2024, organising them into four broad families: demonstration-based prompting (zero-shot and few-shot learning), reasoning-structured prompting (chain-of-thought, self-consistency, tree- and graph-of-thoughts), agentic and tool-augmented prompting (ReAct and reflection-based methods), and optimization-based prompting (automatic prompt engineering and soft/prefix prompt tuning). For each family we summarise representative studies, the benchmarks used to evaluate them, and their reported strengths and limitations. We further propose a comparative framework built around six evaluation criteria – accuracy uplift, inference cost, human engineering effort, robustness, interpretability, and applicability under black-box (API-only) access – and use it to place the surveyed techniques on a common footing. Reported benchmark figures collected from the literature (e.g., chain-of-thought with self-consistency raising PaLM-540B accuracy on GSM8K from 56.5% to 74.4%, and Tree-of-Thoughts raising GPT-4's success rate on the Game of 24 from 4% to 74%) illustrate that large accuracy gains are consistently accompanied by proportionally larger inference-time costs. The survey concludes that no single technique dominates across all criteria, and that the choice of prompting strategy should be guided by task difficulty, latency and cost budgets, and the degree of interpretability required in a given deployment.

References :

[1] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., ... Amodei, D. “Language Models are Few-Shot Learners.” Advances in Neural Information Processing Systems (NeurIPS), 2020. arXiv:2005.14165.

[2] Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.” Advances in Neural Information Processing Systems (NeurIPS), 2022. arXiv:2201.11903.

[3] Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. “Large Language Models are Zero-Shot Reasoners.” Advances in Neural Information Processing Systems (NeurIPS), 2022. arXiv:2205.11916.

[4] Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. “Self-Consistency Improves Chain of Thought Reasoning in Language Models.” International Conference on Learning Representations (ICLR), 2023. arXiv:2203.11171.

[5] Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. “Tree of Thoughts: Deliberate Problem Solving with Large Language Models.” Advances in Neural Information Processing Systems (NeurIPS), 2023. arXiv:2305.10601.

[6] Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Podstawski, M., Gianinazzi, L., Gajda, J., Lehmann, T., Niewiadomski, H., Nyczyk, P., & Hoefler, T. “Graph of Thoughts: Solving Elaborate Problems with Large Language Models.” Proceedings of the AAAI Conference on Artificial Intelligence, 2024. arXiv:2308.09687.

[7] Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. “ReAct: Synergizing Reasoning and Acting in Language Models.” International Conference on Learning Representations (ICLR), 2023. arXiv:2210.03629.

[8] Zhou, Y., Muresanu, A. I., Han, Z., Paster, K., Pitis, S., Chan, H., & Ba, J. “Large Language Models Are Human-Level Prompt Engineers.” International Conference on Learning Representations (ICLR), 2023. arXiv:2211.01910.

[9] Lester, B., Al-Rfou, R., & Constant, N. “The Power of Scale for Parameter-Efficient Prompt Tuning.” Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021. arXiv:2104.08691.

[10] Li, X. L., & Liang, P. “Prefix-Tuning: Optimizing Continuous Prompts for Generation.” Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL-IJCNLP), 2021. arXiv:2101.00190.

[11] Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. “Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.” ACM Computing Surveys, 55(9), 1–35, 2023. arXiv:2107.13586.

[12] Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., Le, Q., & Chi, E. “Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.” International Conference on Learning Representations (ICLR), 2023. arXiv:2205.10625.

[13] Zhang, Z., Zhang, A., Li, M., & Smola, A. “Automatic Chain of Thought Prompting in Large Language Models.” International Conference on Learning Representations (ICLR), 2023. arXiv:2210.03493.

[14] White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. “A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.” Proceedings of the 30th Conference on Pattern Languages of Programs (PLoP), 2023.

[15] Yao, S., Chen, H., Yang, J., & Narasimhan, K. “WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents.” Advances in Neural Information Processing Systems (NeurIPS), 2022. arXiv:2207.01206.

[16] Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. “HotpotQA: A Dataset for Diverse, Explainable Multi-Hop Question Answering.” Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.

[17] Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., Hesse, C., & Schulman, J. “Training Verifiers to Solve Math Word Problems.” arXiv:2110.14168, 2021.

[18] Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., & Tang, J. “GPT Understands, Too.” AI Open, 2023 (originally arXiv:2103.10385, 2021).

[19] Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. “Training Language Models to Follow Instructions with Human Feedback.” Advances in Neural Information Processing Systems (NeurIPS), 2022. arXiv:2203.02155.

Keywords :

Large Language Models, Prompt Engineering, Chain-Of-Thought, In-Context Learning, Tree of Thoughts, React, Self-Consistency, Automatic Prompt Engineering, Comparative Survey.