{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:13:51Z","timestamp":1762838031401,"version":"build-2065373602"},"reference-count":31,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T00:00:00Z","timestamp":1762041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72401286"],"award-info":[{"award-number":["72401286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Innovative reasoning frameworks have been proposed to enhance the reasoning capabilities of AI agents, improving their performance in various tasks. However, most existing research has focused on enhancing designing frameworks for LLMs, with limited attention on leveraging in-context learning to boost their reasoning power. This paper proposes a novel approach, Demo-ToT, which enhances the Tree-of-Thought (ToT) reasoning framework by dynamically retrieving relevant demonstrations to improve reasoning accuracy. Various demonstration retrieval strategies, including vector similarity, sparse retrieval, and string similarity, were explored to identify the most effective methods for optimizing LLM performance. Experiments conducted across multiple benchmarks and language models of varying sizes demonstrated that Demo-ToT substantially enhanced the reasoning ability of smaller LLMs, achieving performance comparable to or even surpassing that of much larger models such as GPT-4.<\/jats:p>","DOI":"10.3390\/bdcc9110276","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:55:22Z","timestamp":1762178122000},"page":"276","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Demo-ToT: Enhancing the Reasoning Capabilities of AI Agent via Improved Demonstrations Retrieval Strategy"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1246-4226","authenticated-orcid":false,"given":"Jiahui","family":"Li","sequence":"first","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangbang","family":"Ren","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengmeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghui","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,2]]},"reference":[{"key":"ref_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Jason","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_2","unstructured":"Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E.H., Narang, S., Chowdhery, A., and Zhou, D. (2023, January 1\u20135). Self-Consistency Improves Chain of Thought Reasoning in Language Models. Proceedings of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_3","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Podstawski, M., Gianinazzi, L., Gajda, J., Lehmann, T., Niewiadomski, H., and Nyczyk, P. (2024, January 20\u201327). Graph of thoughts: Solving elaborate problems with large language models. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref_5","first-page":"12588","article-title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","volume":"53","author":"Chen","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref_6","unstructured":"Zhang, Z., Zhang, A., Li, M., and Smola, A. (2023, January 1\u20135). Automatic Chain of Thought Prompting in Large Language Models. Proceedings of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zeng, H., Killingback, J., and Zamani, H. (2025, January 13\u201318). Scaling sparse and dense retrieval in decoder-only llms. Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua, Italy.","DOI":"10.1145\/3726302.3730225"},{"key":"ref_8","first-page":"151","article-title":"Comparative Analysis of Text Similarity Algorithms and Their Practical Applications in Computer Science","volume":"92","author":"Poljak","year":"2025","journal-title":"Elektrotehn. Vestn."},{"key":"ref_9","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1\u20135). React: Synergizing reasoning and acting in language models. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_10","unstructured":"Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., and Neubig, G. (2023, January 23\u201329). Pal: Program-aided language models. Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"95574","DOI":"10.1109\/ACCESS.2025.3575303","article-title":"In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning","volume":"13","author":"Basiouni","year":"2025","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pryzant, R., Iter, D., Li, J., Lee, Y.T., Zhu, C., and Zeng, M. (2023, January 6\u201310). Automatic Prompt Optimization with \u201cGradient Descent\u201d and Beam Search. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.494"},{"key":"ref_13","unstructured":"Zhou, Y., Zheng, B., and Chen, Q. (2024, January 11\u201316). Large Language Models as Automatic Prompt Engineers. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand."},{"key":"ref_14","unstructured":"Chen, Z., Zhang, H., and Liu, X. (2024, January 16). Soft Prompt Transfer for Parameter-Efficient Fine-Tuning of Large Language Models. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhou,, X., Liang, D., Xu, W., Zhu, X., Xu, Y., Zou, Z., and Bai, X. (2024). Dynamic adapter meets prompt tuning: Parameter-efficient transfer learning for point cloud analysis. arXiv.","DOI":"10.1109\/CVPR52733.2024.01393"},{"key":"ref_16","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., hsin Chi, E.H., Xia, F., Le, Q., and Zhou, D. (2022). Chain of Thought Prompting Elicits Reasoning in Large Language Models. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, R., Liu, H., Nag, S., Dai, Z., Xie, Y., Tang, X., Luo, C., Li, Y., Ho, J.C., and Yang, C. (May, January 29). SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains. Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2025), Albuquerque, NM, USA.","DOI":"10.18653\/v1\/2025.naacl-long.575"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, X., Lv, K., Yan, H., Lin, T., Zhu, W., Ni, Y., Xie, G.T., Wang, X., and Qiu, X. (2023). Unified Demonstration Retriever for In-Context Learning. arXiv.","DOI":"10.18653\/v1\/2023.acl-long.256"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Feng, S., and Tan, C. (2022, January 7\u201311). Active Example Selection for In-Context Learning. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.622"},{"key":"ref_20","unstructured":"Li, G., Wang, P., Liu, J., Guo, Y., Ji, K., Shang, Z., and Xu, Z. (2024, January 3\u20139). Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), Jeju, Republic of Korea."},{"key":"ref_21","unstructured":"Li, X., Nie, E., and Liang, S. (2023). From classification to generation: Insights into crosslingual retrieval augmented icl. arXiv."},{"key":"ref_22","unstructured":"Touvron, H., Martin, L., Stone, K.R., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., and Bhosale, S. (2023). Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3951","DOI":"10.14778\/3749646.3749666","article-title":"Cracking Vector Search Indexes","volume":"18","author":"Mageirakos","year":"2025","journal-title":"Proc. VLDB Endow."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"13371","DOI":"10.18653\/v1\/2025.acl-long.656","article-title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","volume":"Volume 1: Long Papers","author":"Zhao","year":"2025","journal-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dong, Q., Li, L., Dai, D., Zheng, C., Ma, J., Li, R., Xia, H., Xu, J., Wu, Z., and Liu, T. (2024, January 12\u201316). A Survey on In-Context Learning. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA.","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref_26","unstructured":"Daniel, L., and Lincoln, M. (2024). HumanEval on Latest GPT Models-2024. arXiv."},{"key":"ref_27","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., and Wei, H. (2024). Qwen2. 5 technical report. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kempton, T., and Burrell, S. (2025). Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models. arXiv.","DOI":"10.18653\/v1\/2025.findings-emnlp.1210"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., and Nie, J.Y. (2024, January 14\u201318). C-pack: Packed resources for general chinese embeddings. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Washington, DC, USA.","DOI":"10.1145\/3626772.3657878"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Warner, B., Chaffin, A., Clavi\u00e9, B., Weller, O., Hallstr\u00f6m, O., Taghadouini, S., Gallagher, A., Biswas, R., Ladhak, F., and Aarsen, T. (2024). Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference. arXiv.","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Xu, J., Shao, W., Chen, L., and Liu, L. (2023, January 6\u201310). SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.737"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/11\/276\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:10:38Z","timestamp":1762837838000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/11\/276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,2]]},"references-count":31,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["bdcc9110276"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9110276","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,11,2]]}}}