Abstract
Large language models (LLMs) demonstrate strong reasoning and planning capabilities in static textual contexts, yet they struggle significantly with dynamic decision-making tasks involving spatial elements, such as point selection in military simulations. These limitations arise from their reduced capacity to integrate real-time geographic data and adapt to spatial conditions, which can lead to crucial errors in positioning decisions. Such deficiencies may result in missed opportunities for tactical advantages, increased vulnerability, and diminished overall effectiveness in combat scenarios. To mitigate these issues, this paper presents the Geo-Commander framework, an innovative multi-task agent to combat simulations by integrate the ReAct reasoning mechanism and spatial encoding. The Geo-Choice module of this framework employs hexagonal grid encoding for preliminary location screening, enabling the agent to establish spatial constraints early in the decision-making process. The ReAct chain of this framework incorporates detailed geographic insights into the reasoning loop, yielding interpretable decisions for point selection. We validate the framework through experiments that reveal substantial performance improvements in both static point selections and real-time dynamic command tasks within a tank detachment combat simulation environment. Results indicate that Geo-Commander consistently surpasses control groups across various metrics, including selection quality, win rate, and overall combat effectiveness. These performance metrics highlight the framework’s potential to meet the demands of dynamic combat environments, ultimately confirming the feasibility of integrating spatial reasoning within LLM frameworks and opening avenues for advancements in multi-agent geospatial intelligence systems and battlefield decision-making support.
Data availability
The data that support the findings of this study are openly available in ScienceDB at https://doi.org/10.57760/sciencedb.32513, reference number24.
References
Yao, S. et al. React: SYnergizing reasoning and acting in language models. In: 11th International Conference on Learning Representations, (ICLR, 2023).
Shinn, N. et al. Reflexion: language agents with verbal reinforcement learning: In: 37th conference on neural information processing systems. (NeurIPS, 2023).
Wang, G. et al. VOYAGER: An open-ended embodied agent with large language models. arXiv, (2023).
Jafarnejad, S. MapLLM - A blueprint for improving geospatial reasoning in LLMs. (2025).
Cheng, A. et al. SpatialRGPT: Grounded spatial reasoning in vision-language models. In: 38th Conference on Neural Information Processing Systems, NeurIPS 2024.
Headquarters, D. & O T A. FM3-34.230-Topographic Operations. (2000).
Goecks, V. G. & Waytowich, N. C. O. A. G. P. T. Generative pre-trained transformers for accelerated course of action development in military operations. In: 2024 International Conference on Military Communication and Information Systems (ICMCIS), 2024.
Cao, X. et al. MAPLM: A real-world large-scale vision-language benchmark for map and traffic scene understanding. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024.
Zhang, Y. et al. GeoGPT: understanding and processing geospatial tasks through an autonomous GPT. arXiv, (2023).
Chen, B. et al. SpatialVLM: Endowing vision-language models with spatial reasoning capabilities. In: 2024 IEEE/CVF Conference on Computer Vision and (CVPR), 2024.
Huang, C. et al. Visual language maps for robot navigation.In: 2023 IEEE International Conference on Robotics and (ICRA), 2023.
Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529 (7587), 484–489 (2016).
Wu, D. J. Accelerating Self-Play Learning in Go. Statistics,2. (2019)
Birch, C. P., D C, Oom, S. P. & Beecham, J. A. Rectangular and hexagonal grids used for observation, experiment and simulation in ecology. Ecol. Model. 206 (3–4), 347–359 (2007).
Tang, F. Zhang Xin,You Xiong,et al. Design Method of Tactical Level Hexagonal Wargame Map. J. Syst. Simul. 31 (5), 869–878 (2019).
Srivastava, V. et al. MapIQ: Benchmarking multimodal large language models for map question answering. (2025).
R A I, P. S. et al. Light-MLLMAD: A lightweight multimodal large language model for one-shot industrial visual anomaly detection. (2025).
Ruan, J. et al. MME-SCI: A comprehensive and challenging science benchmark for multimodal large language models. (2025).
Headquarters, D. & O T A. FM 3-21.8 - The Infantry Rifle Platoon and Squad. (2007).
Headquarters, D. & O T A. FM 3-06.11 - Camouflage, Concealment, and Cover. (2002).
Headquarters, D. & O T A. FM 3-05.222 / TC 23 – 14 - Sniper Training and Employment. (2003).
Zhou, Z. & Zhao, H. Design and implementation of B/S architecture-based wargaming system.J. Equip. Acad. 27 (2), 68–72 (2016).
Yin, Q. et al. Intelligent decision-making technologies and challenges in wargaming. Acta Automatica Sinica. 49 (5), 913–928 (2023).
Chen, Y. Experimental data of geo-commander[DS/OL]. Sci. Data Bank.,(2025). https://doi.org/10.57760/sciencedb.32513
Acknowledgements
We would like to express our sincere gratitude to the military experts who contributed their professional knowledge and time to this study. Specifically, we thank the Army Commander, the Army Staff Officer, and the two wargaming experts for their in-depth analysis of the combat simulation scenarios and for their crucial role in developing the grid point quality rating table through discussion. Their expertise ensured the tactical relevance and validity of our experimental evaluation metrics.
Author information
Authors and Affiliations
Contributions
Conceptualization, Yibo Chen; methodology, Caleb Jojo; software, Yibo Chen; validation, Shuhang Zhou; formal analysis, Shuhang Zhou; investigation, Caleb Jojo; resources, Yang Ping; data curation, Shuhang Zhou; writing—original draft preparation, Yibo Chen; writing—review and editing, Yang Ping; visualization, Caleb Jojo; supervision, Yang Ping; project administration, Yang Ping; funding acquisition, Yang Ping. All authors agree to be accountable for all aspects of the work.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Informed Consent
All participants (the four military experts) employed in this study were adults. Before their participation, all individuals were fully informed about the purpose of the study, the procedures involved, and how their input would be used. Written informed consent was obtained from all participants before their involvement in the study.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Chen, Yb., Ping, Y., Zhou, S. et al. A framework of large language model commander agent for spatial reasoning in combat simulation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-43365-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-43365-3
