{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T15:33:01Z","timestamp":1772638381355,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Recent advancements in planning prompting techniques for Large Language Models have improved their reasoning, planning, and action abilities. This paper develops a planning framework for Large Language Models using model predictive control that enables them to iteratively solve complex problems with long horizons. We show that in the model predictive control formulation, LLM planners act as approximate cost function optimizers and solve complex problems by breaking them down into smaller iterative steps. With our proposed planning framework, we demonstrate improved performance over few-shot prompting and improved efficiency over Monte Carlo Tree Search on several planning benchmarks.<\/jats:p>","DOI":"10.3390\/computers14030104","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T04:29:28Z","timestamp":1742185768000},"page":"104","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["LLMPC: Large Language Model Predictive Control"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9338-4709","authenticated-orcid":false,"given":"Gabriel","family":"Maher","sequence":"first","affiliation":[{"name":"Independent Researcher, San Francisco, CA 94115, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,15]]},"reference":[{"key":"ref_1","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv."},{"key":"ref_2","unstructured":"Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., and Zhou, D. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models. arXiv."},{"key":"ref_3","unstructured":"Wang, A., Song, L., Tian, Y., Peng, B., Yu, D., Mi, H., Su, J., and Yu, D. (2024). LiteSearch: Efficacious Tree Search for LLM. arXiv."},{"key":"ref_4","unstructured":"Jiang, J., Chen, Z., Min, Y., Chen, J., Cheng, X., Wang, J., Tang, Y., Sun, H., Deng, J., and Zhao, W.X. (2024). Enhancing LLM Reasoning with Reward-guided Tree Search. arXiv."},{"key":"ref_5","unstructured":"DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., and Wang, P. (2025). DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv."},{"key":"ref_6","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., and Hausman, K. (2022). Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv."},{"key":"ref_7","unstructured":"Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., and Anandkumar, A. (2023). Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Song, C.H., Wu, J., Washington, C., Sadler, B.M., Chao, W.L., and Su, Y. (2023, January 2\u20133). LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref_9","unstructured":"Zhu, Y., Qiao, S., Ou, Y., Deng, S., Zhang, N., Lyu, S., Shen, Y., Liang, L., Gu, J., and Chen, H. (2024). KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents. arXiv."},{"key":"ref_10","unstructured":"Yin, S., Pang, X., Ding, Y., Chen, M., Bi, Y., Xiong, Y., Huang, W., Xiang, Z., Shao, J., and Chen, S. (2024). SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents. arXiv."},{"key":"ref_11","unstructured":"Singh, I., Traum, D., and Thomason, J. (2024). TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Song, J., Yao, K., Shu, Z., and Ma, L. (2024, January 13\u201317). ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan.","DOI":"10.1109\/ICRA57147.2024.10610065"},{"key":"ref_13","unstructured":"Zhang, C., Deik, D.G.X., Li, D., Zhang, H., and Liu, Y. (2024). Planning with Multi-Constraints via Collaborative Language Agents. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hao, S., Gu, Y., Ma, H., Hong, J.J., Wang, Z., Wang, D.Z., and Hu, Z. (2023). Reasoning with Language Model is Planning with World Model. arXiv.","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref_15","unstructured":"Putta, P., Mills, E., Garg, N., Motwani, S., Finn, C., Garg, D., and Rafailov, R. (2024). Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents. arXiv."},{"key":"ref_16","unstructured":"Light, J., Wu, Y., Sun, Y., Yu, W., Liu, Y., Zhao, X., Hu, Z., Chen, H., and Cheng, W. (2024). Scattered Forest Search: Smarter Code Space Exploration with LLMs. arXiv."},{"key":"ref_17","unstructured":"Wang, E., Cassano, F., Wu, C., Bai, Y., Song, W., Nath, V., Han, Z., Hendryx, S., Yue, S., and Zhang, H. (2024). Planning In Natural Language Improves LLM Search For Code Generation. arXiv."},{"key":"ref_18","unstructured":"Gu, Y., Zheng, B., Gou, B., Zhang, K., Chang, C., Srivastava, S., Xie, Y., Qi, P., Sun, H., and Su, Y. (2024). Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents. arXiv."},{"key":"ref_19","unstructured":"Chae, H., Kim, N., Iunn Ong, K.T., Gwak, M., Song, G., Kim, J., Kim, S., Lee, D., and Yeo, J. (2024). Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation. arXiv."},{"key":"ref_20","unstructured":"Chen, Y., Pesaranghader, A., Sadhu, T., and Yi, D.H. (2024). Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let\u2019s Take TravelPlanner as an Example. arXiv."},{"key":"ref_21","unstructured":"Xiong, S., Payani, A., Yang, Y., and Fekri, F. (2024). Deliberate Reasoning for LLMs as Structure-aware Planning with Accurate World Model. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Paul, S.K. (2024, January 25\u201327). Continually Learning Planning Agent for Large Environments guided by LLMs. Proceedings of the 2024 IEEE Conference on Artificial Intelligence (CAI), Singapore.","DOI":"10.1109\/CAI59869.2024.00076"},{"key":"ref_23","unstructured":"Peng, B., Li, C., He, P., Galley, M., and Gao, J. (2023). Instruction Tuning with GPT-4. arXiv."},{"key":"ref_24","unstructured":"Ghosh, S., Evuru, C.K.R., Kumar, S., S, R., Aneja, D., Jin, Z., Duraiswami, R., and Manocha, D. (2024). A Closer Look at the Limitations of Instruction Tuning. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"Mayne","year":"2000","journal-title":"Automatica"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1007\/s00170-021-07682-3","article-title":"Review on model predictive control: An engineering perspective","volume":"117","author":"Schwenzer","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108554","DOI":"10.1016\/j.compchemeng.2023.108554","article-title":"Robust predictive fault-tolerant switching control for discrete linear systems with actuator random failures","volume":"181","author":"Shi","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"ref_28","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., and Choi, Y. (2020). The Curious Case of Neural Text Degeneration. arXiv."},{"key":"ref_29","unstructured":"Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., and Qian, B. (2023). ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. arXiv."},{"key":"ref_30","unstructured":"Guo, P.F., Chen, Y.H., Tsai, Y.D., and Lin, S.D. (2024). Towards Optimizing with Large Language Models. arXiv."},{"key":"ref_31","unstructured":"Jiang, C., Shu, X., Qian, H., Lu, X., Zhou, J., Zhou, A., and Yu, Y. (2025). LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch. arXiv."},{"key":"ref_32","unstructured":"Li, H., Li, Y., Tian, A., Tang, T., Xu, Z., Chen, X., Hu, N., Dong, W., Li, Q., and Chen, L. (2025). A Survey on Large Language Model Acceleration based on KV Cache Management. arXiv."},{"key":"ref_33","unstructured":"Hafez, A., Akhormeh, A.N., Hegazy, A., and Alanwar, A. (2025). Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis. arXiv."},{"key":"ref_34","unstructured":"Wu, Y., Xiong, Z., Hu, Y., Iyengar, S.S., Jiang, N., Bera, A., Tan, L., and Jagannathan, S. (2025). SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hua, W., Yang, X., Jin, M., Li, Z., Cheng, W., Tang, R., and Zhang, Y. (2024). TrustAgent: Towards Safe and Trustworthy LLM-based Agents. arXiv.","DOI":"10.18653\/v1\/2024.findings-emnlp.585"},{"key":"ref_36","unstructured":"Zheng, H.S., Mishra, S., Zhang, H., Chen, X., Chen, M., Nova, A., Hou, L., Cheng, H.T., Le, Q.V., and Zhou, D. (2025). Natural Plan: Benchmarking LLMs on Natural Language Planning. arXiv."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/3\/104\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:54:26Z","timestamp":1760028866000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/3\/104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,15]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["computers14030104"],"URL":"https:\/\/doi.org\/10.3390\/computers14030104","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,15]]}}}