From Cognition to Simulation: A Systematic Mapping of Visualisation and Interaction in Multi-Agent System
Resumo
Multi-Agent Systems have achieved high cognitive complexity, but their experimentation is hindered by architectural limitations and the rigid coupling between cognition and visualisation in current simulation platforms. To investigate this scenario, we present a systematic literature mapping based on an adaptation of PRISMA and Kitchenham’s methodologies. The analysis revealed three critical gaps: a lack of standardised integration, a conflict between 3D realism and flexibility, and low usability due to hardcoded programming. These results demonstrate the need to develop decoupled architectures. The delegation of the logical deliberation cycle to cognitive frameworks and volumetric rendering to game engines, interconnecting them via standardised asynchronous communication bridges, emerges as the structural pathway to provide an efficient and scalable visual infrastructure for research in the field.Referências
Abar, S., Theodoropoulos, G. K., Lemarinier, P., and O’Hare, G. M. P. (2017). Agent based modelling and simulation tools: A review of the state-of-art software. Computer Science Review, 24:13–33.
Al Shukairi, H. and Cardoso, R. C. (2023). ML-MAS: A hybrid AI framework for self-driving vehicles. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, page 1191–1199. International Foundation for Autonomous Agents and Multiagent Systems.
Angelotti, G. and Díaz-Rodríguez, N. (2023). Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using myerson values. Knowledge-Based Systems, 260:110189.
Bahamid, A., Mohd Ibrahim, A., and Shafie, A. A. (2024). Crowd evacuation with human-level intelligence via neuro-symbolic approach. Advanced Engineering Informatics, 60:102356.
Beeching, E., Debangoye, J., Simonin, O., and Wolf, C. (2021). Godot reinforcement learning agents. arXiv preprint. Version v1, 7 Dec 2021.
Cai, Z., Cardenas, C. R., Leo, K., Zhang, C., Backman, K., Li, H., Li, B., Ghorbanali, M., Datta, S., Qu, L., Gutierrez, J., Ignatiev, A., Li, Y.-F., Vered, M., Stuckey, P. J., de la Banda, M. G., and Rezatofighi, H. (2025). Neusis: A compositional neuro-symbolic framework for autonomous perception, reasoning, and planning in complex uav search missions. IEEE Robotics and Automation Letters, 10(9):9502–9509.
Chen, Y., Arkin, J., Zhang, Y., Roy, N., and Fan, C. (2024). Scalable multi-robot collaboration with large language models: Centralized or decentralized systems? In 2024 IEEE International Conference on Robotics and Automation (ICRA), page 4311–4317. IEEE.
Dang-Nhu, R. (2020). Plans: neuro-symbolic program learning from videos. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA. Curran Associates Inc.
de Mello, R. R. P., de Santiago, R., Silveira, R. A., and Gelaim, T. A. (2024). Neural-symbolic bdi-agent as a multi-context system: A case study with negotiating agent. Expert Systems with Applications, 238:121656.
Deane, O. and Ray, O. (2025). Symplex: Learning social norm hierarchies by combining autonomous exploration and expert imitation. In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS ’25, page 2493–2495, Richland, SC. International Foundation for Autonomous Agents and Multiagent Systems.
Du, Q., Gray, A., Li, B., Li, Z., Luo, J., Ravikumar, P., Scherer, S., Si, X., Stepputtis, S., Sycara, K., Wang, C., Wang, W., and Xie, Y. (2024). Logicity: Advancing neuro-symbolic ai with abstract urban simulation. In Advances in Neural Information Processing Systems 37, NeurIPS 2024, page 69840–69864. Neural Information Processing Systems Foundation, Inc. (NeurIPS).
Eichelbeck, M., Markgraf, H., and Althoff, M. (2026). Commonpower: A framework for safe data-driven smart grid control. IEEE Transactions on Smart Grid, 17(1):71–82.
Ghallab, M., Nau, D., and Traverso, P. (2025). Acting, Planning, and Learning. Cambridge University Press.
Goel, S., Lymperopoulos, P., Thielstrom, R., Krause, E., Feeney, P., Lorang, P., Schneider, S., Wei, Y., Kildebeck, E., Goss, S., Hughes, M. C., Liu, L., Sinapov, J., and Scheutz, M. (2024). A neurosymbolic cognitive architecture framework for handling novelties in open worlds. Artificial Intelligence, 331:104111.
Grosvenor, A., Zemlyansky, A., Wahab, A., Bohachov, K., Dogan, A., and Deighan, D. (2025). Hybrid intelligence systems for reliable automation: advancing knowledge work and autonomous operations with scalable ai architectures. Frontiers in Robotics and AI, 12.
Juliani, A., Berges, V.-P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., Mattar, M., Lange, D., et al. (2020). Unity: A general platform for intelligent agents. arXiv preprint arXiv:1809.02627. arXiv:1809.02627v2, 6 May 2020.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. EBSE Technical Report EBSE-2007-01, Software Engineering Group, School of Computer Science and Mathematics, Keele University and Department of Computer Science, University of Durham. Version 2.3. Dated 9 July 2007.
Labiosa, A., Wang, Z., Agarwal, S., Cong, W., Hemkumar, G., Harish, A. N., Hong, B., Kelle, J., Li, C., Li, Y., Shao, Z., Stone, P., and Hanna, J. P. (2025). Reinforcement learning within the classical robotics stack: A case study in robot soccer. In 2025 IEEE International Conference on Robotics and Automation (ICRA), page 14999–15006. IEEE.
Lazarin, N., Pantoja, C., and Viterbo, J. (2026). My body, my perceptions: A shift from computationalism to embodied cognition in bdi-agent-based embedded systems. In Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems, AAMAS ’26, page 800–809, Richland, SC. International Foundation for Autonomous Agents and Multiagent Systems.
Liu, B., Jiang, Y., Zhang, X., Liu, Q., Zhang, S., Biswas, J., and Stone, P. (2023). Llm+p: Empowering large language models with optimal planning proficiency.
Lorang, P., Goel, S., Shukla, Y., Zips, P., and Scheutz, M. (2024). A framework for neurosymbolic goal-conditioned continual learning in open world environments. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 12070–12077. IEEE.
Mellado, A. L. L., Neres, G. G., Borges, A. P., Cardoso, R. C., and Alves, G. V. (2026). MASPY: A Python Framework for Developing BDI Agents with Reinforcement Learning, page 4074–4076. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC.
Mellado, A. L. L., Pinz Borges, A., and Alves, G. V. (2025). Maspy: A python-based framework for developing bdi multi-agent systems. In Advances in Practical Applications of Agents, Multi-Agent Systems, and Computational Social Science: The PAAMS Collection, pages 216–227, Cham. Springer Nature Switzerland.
Moon, J. (2021). Plugin framework-based neuro-symbolic grounded task planning for multi-agent system. Sensors, 21(23):7896.
Núñez-Molina, C. (2022). Application of neurosymbolic ai to sequential decision making. In Raedt, L. D., editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 5863–5864. International Joint Conferences on Artificial Intelligence Organization. Doctoral Consortium.
Rajvanshi, A., Sikka, K., Lin, X., Lee, B., Chiu, H.-P., and Velasquez, A. (2024). Saynav: Grounding large language models for dynamic planning to navigation in new environments. Proceedings of the International Conference on Automated Planning and Scheduling, 34:464–474.
Rakhman, U., Ahn, J., and Nam, C. (2021). Fully automatic data collection for neuro-symbolic task planning for mobile robot navigation. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), page 450–455. IEEE.
Rehm, J., Reshodko, I., Børresen, S. Z., and Gundersen, O. E. (2024). The virtual driving instructor: Multi-agent system collaborating via knowledge graph for scalable driver education. AI Magazine, 45(4):514–525.
Schrittwieser, J., Antonoglou, I., Hubert, T., Simonyan, K., Sifre, L., Schmitt, S., Guez, A., Lockhart, E., Hassabis, D., Graepel, T., Lillicrap, T., and Silver, D. (2020). Mastering atari, go, chess and shogi by planning with a learned model. Nature, 588(7839):604–609.
Schuck, M., Dahanaggamaarachchi, D. O., Sprenger, B., Vyas, V., Zhou, S., and Schoellig, A. P. (2025). Swarmgpt: Combining large language models with safe motion planning for drone swarm choreography. IEEE Robotics and Automation Letters, 10(11):12237–12244.
Sharif, M., Yasmin, M., Hussain, S., and Shah, J. H. (2020). A review of reinforcement learning based medical image analysis. Multimedia Tools and Applications, 79(31):22621–22652.
Silver, T., Chitnis, R., Curtis, A., Tenenbaum, J. B., Lozano-Pérez, T., and Kaelbling, L. P. (2021). Planning with learned object importance in large problem instances using graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13):11962–11971.
Sohn, S., Woo, H., Choi, J., and Lee, H. (2020). Meta reinforcement learning with autonomous inference of subtask dependencies.
Sovrano, F., Raymond, A., and Prorok, A. (2022). Explanation-aware experience replay in rule-dense environments. IEEE Robotics and Automation Letters, 7(2):898–905.
Subramanian, C., Liu, M., Khan, N., Lenchner, J., Amarnath, A., Swaminathan, S., Riegel, R., and Gray, A. (2024). A neuro-symbolic approach to multi-agent rl for interpretability and probabilistic decision making.
Thilak, K. R. and Chandrasekar, P. (2025). Modeling and simulation of anaerobic digestion-gasification integration using madrl-fahp. Biofuels, 0(0):1–24.
Uddin, M. S., Ahmed, A., Aktarujjaman, M., Monirujjaman, M., Ahmed, M., Mridha, M. F., and Hossen, M. J. (2025). A hybrid reinforcement learning and knowledge graph framework for financial risk optimization in healthcare systems. Scientific Reports, 15(1):29057.
Wang, G., Wei, F., Jiang, Y., Zhao, M., Wang, K., and Qi, H. (2022). A multi-auv maritime target search method for moving and invisible objects based on multi-agent deep reinforcement learning. Sensors, 22(21).
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.
Wooldridge, M. (2009). An Introduction to MultiAgent Systems. John Wiley & Sons, 2 edition.
Xu, J., Wang, H., Niu, Z., Wu, H., and Che, W. (2020). Knowledge graph grounded goal planning for open-domain conversation generation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):9338–9345.
Yaw, C. T., Yap, K. S., Wong, S. Y., Yap, H. J., and Paw, J. K. S. (2020). Enhancement of neural network based multi agent system for classification and regression in energy system. IEEE Access, 8:163026–163043.
Zellers, R., Holtzman, A., Peters, M., Mottaghi, R., Kembhavi, A., Farhadi, A., and Choi, Y. (2021). Piglet: Language grounding through neuro-symbolic interaction in a 3d world. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), page 2040–2050. Association for Computational Linguistics.
Zhang, H., Du, W., Shan, J., Zhou, Q., Du, Y., Tenenbaum, J. B., Shu, T., and Gan, C. (2024). Building cooperative embodied agents modularly with large language models.
Zhang, L., Ford, V., Chen, Z., and Chen, J. (2025). Automatic building energy model development and debugging using large language models agentic workflow. Energy and Buildings, 327:115116.
Al Shukairi, H. and Cardoso, R. C. (2023). ML-MAS: A hybrid AI framework for self-driving vehicles. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, page 1191–1199. International Foundation for Autonomous Agents and Multiagent Systems.
Angelotti, G. and Díaz-Rodríguez, N. (2023). Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using myerson values. Knowledge-Based Systems, 260:110189.
Bahamid, A., Mohd Ibrahim, A., and Shafie, A. A. (2024). Crowd evacuation with human-level intelligence via neuro-symbolic approach. Advanced Engineering Informatics, 60:102356.
Beeching, E., Debangoye, J., Simonin, O., and Wolf, C. (2021). Godot reinforcement learning agents. arXiv preprint. Version v1, 7 Dec 2021.
Cai, Z., Cardenas, C. R., Leo, K., Zhang, C., Backman, K., Li, H., Li, B., Ghorbanali, M., Datta, S., Qu, L., Gutierrez, J., Ignatiev, A., Li, Y.-F., Vered, M., Stuckey, P. J., de la Banda, M. G., and Rezatofighi, H. (2025). Neusis: A compositional neuro-symbolic framework for autonomous perception, reasoning, and planning in complex uav search missions. IEEE Robotics and Automation Letters, 10(9):9502–9509.
Chen, Y., Arkin, J., Zhang, Y., Roy, N., and Fan, C. (2024). Scalable multi-robot collaboration with large language models: Centralized or decentralized systems? In 2024 IEEE International Conference on Robotics and Automation (ICRA), page 4311–4317. IEEE.
Dang-Nhu, R. (2020). Plans: neuro-symbolic program learning from videos. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA. Curran Associates Inc.
de Mello, R. R. P., de Santiago, R., Silveira, R. A., and Gelaim, T. A. (2024). Neural-symbolic bdi-agent as a multi-context system: A case study with negotiating agent. Expert Systems with Applications, 238:121656.
Deane, O. and Ray, O. (2025). Symplex: Learning social norm hierarchies by combining autonomous exploration and expert imitation. In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS ’25, page 2493–2495, Richland, SC. International Foundation for Autonomous Agents and Multiagent Systems.
Du, Q., Gray, A., Li, B., Li, Z., Luo, J., Ravikumar, P., Scherer, S., Si, X., Stepputtis, S., Sycara, K., Wang, C., Wang, W., and Xie, Y. (2024). Logicity: Advancing neuro-symbolic ai with abstract urban simulation. In Advances in Neural Information Processing Systems 37, NeurIPS 2024, page 69840–69864. Neural Information Processing Systems Foundation, Inc. (NeurIPS).
Eichelbeck, M., Markgraf, H., and Althoff, M. (2026). Commonpower: A framework for safe data-driven smart grid control. IEEE Transactions on Smart Grid, 17(1):71–82.
Ghallab, M., Nau, D., and Traverso, P. (2025). Acting, Planning, and Learning. Cambridge University Press.
Goel, S., Lymperopoulos, P., Thielstrom, R., Krause, E., Feeney, P., Lorang, P., Schneider, S., Wei, Y., Kildebeck, E., Goss, S., Hughes, M. C., Liu, L., Sinapov, J., and Scheutz, M. (2024). A neurosymbolic cognitive architecture framework for handling novelties in open worlds. Artificial Intelligence, 331:104111.
Grosvenor, A., Zemlyansky, A., Wahab, A., Bohachov, K., Dogan, A., and Deighan, D. (2025). Hybrid intelligence systems for reliable automation: advancing knowledge work and autonomous operations with scalable ai architectures. Frontiers in Robotics and AI, 12.
Juliani, A., Berges, V.-P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., Mattar, M., Lange, D., et al. (2020). Unity: A general platform for intelligent agents. arXiv preprint arXiv:1809.02627. arXiv:1809.02627v2, 6 May 2020.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. EBSE Technical Report EBSE-2007-01, Software Engineering Group, School of Computer Science and Mathematics, Keele University and Department of Computer Science, University of Durham. Version 2.3. Dated 9 July 2007.
Labiosa, A., Wang, Z., Agarwal, S., Cong, W., Hemkumar, G., Harish, A. N., Hong, B., Kelle, J., Li, C., Li, Y., Shao, Z., Stone, P., and Hanna, J. P. (2025). Reinforcement learning within the classical robotics stack: A case study in robot soccer. In 2025 IEEE International Conference on Robotics and Automation (ICRA), page 14999–15006. IEEE.
Lazarin, N., Pantoja, C., and Viterbo, J. (2026). My body, my perceptions: A shift from computationalism to embodied cognition in bdi-agent-based embedded systems. In Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems, AAMAS ’26, page 800–809, Richland, SC. International Foundation for Autonomous Agents and Multiagent Systems.
Liu, B., Jiang, Y., Zhang, X., Liu, Q., Zhang, S., Biswas, J., and Stone, P. (2023). Llm+p: Empowering large language models with optimal planning proficiency.
Lorang, P., Goel, S., Shukla, Y., Zips, P., and Scheutz, M. (2024). A framework for neurosymbolic goal-conditioned continual learning in open world environments. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 12070–12077. IEEE.
Mellado, A. L. L., Neres, G. G., Borges, A. P., Cardoso, R. C., and Alves, G. V. (2026). MASPY: A Python Framework for Developing BDI Agents with Reinforcement Learning, page 4074–4076. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC.
Mellado, A. L. L., Pinz Borges, A., and Alves, G. V. (2025). Maspy: A python-based framework for developing bdi multi-agent systems. In Advances in Practical Applications of Agents, Multi-Agent Systems, and Computational Social Science: The PAAMS Collection, pages 216–227, Cham. Springer Nature Switzerland.
Moon, J. (2021). Plugin framework-based neuro-symbolic grounded task planning for multi-agent system. Sensors, 21(23):7896.
Núñez-Molina, C. (2022). Application of neurosymbolic ai to sequential decision making. In Raedt, L. D., editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 5863–5864. International Joint Conferences on Artificial Intelligence Organization. Doctoral Consortium.
Rajvanshi, A., Sikka, K., Lin, X., Lee, B., Chiu, H.-P., and Velasquez, A. (2024). Saynav: Grounding large language models for dynamic planning to navigation in new environments. Proceedings of the International Conference on Automated Planning and Scheduling, 34:464–474.
Rakhman, U., Ahn, J., and Nam, C. (2021). Fully automatic data collection for neuro-symbolic task planning for mobile robot navigation. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), page 450–455. IEEE.
Rehm, J., Reshodko, I., Børresen, S. Z., and Gundersen, O. E. (2024). The virtual driving instructor: Multi-agent system collaborating via knowledge graph for scalable driver education. AI Magazine, 45(4):514–525.
Schrittwieser, J., Antonoglou, I., Hubert, T., Simonyan, K., Sifre, L., Schmitt, S., Guez, A., Lockhart, E., Hassabis, D., Graepel, T., Lillicrap, T., and Silver, D. (2020). Mastering atari, go, chess and shogi by planning with a learned model. Nature, 588(7839):604–609.
Schuck, M., Dahanaggamaarachchi, D. O., Sprenger, B., Vyas, V., Zhou, S., and Schoellig, A. P. (2025). Swarmgpt: Combining large language models with safe motion planning for drone swarm choreography. IEEE Robotics and Automation Letters, 10(11):12237–12244.
Sharif, M., Yasmin, M., Hussain, S., and Shah, J. H. (2020). A review of reinforcement learning based medical image analysis. Multimedia Tools and Applications, 79(31):22621–22652.
Silver, T., Chitnis, R., Curtis, A., Tenenbaum, J. B., Lozano-Pérez, T., and Kaelbling, L. P. (2021). Planning with learned object importance in large problem instances using graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13):11962–11971.
Sohn, S., Woo, H., Choi, J., and Lee, H. (2020). Meta reinforcement learning with autonomous inference of subtask dependencies.
Sovrano, F., Raymond, A., and Prorok, A. (2022). Explanation-aware experience replay in rule-dense environments. IEEE Robotics and Automation Letters, 7(2):898–905.
Subramanian, C., Liu, M., Khan, N., Lenchner, J., Amarnath, A., Swaminathan, S., Riegel, R., and Gray, A. (2024). A neuro-symbolic approach to multi-agent rl for interpretability and probabilistic decision making.
Thilak, K. R. and Chandrasekar, P. (2025). Modeling and simulation of anaerobic digestion-gasification integration using madrl-fahp. Biofuels, 0(0):1–24.
Uddin, M. S., Ahmed, A., Aktarujjaman, M., Monirujjaman, M., Ahmed, M., Mridha, M. F., and Hossen, M. J. (2025). A hybrid reinforcement learning and knowledge graph framework for financial risk optimization in healthcare systems. Scientific Reports, 15(1):29057.
Wang, G., Wei, F., Jiang, Y., Zhao, M., Wang, K., and Qi, H. (2022). A multi-auv maritime target search method for moving and invisible objects based on multi-agent deep reinforcement learning. Sensors, 22(21).
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.
Wooldridge, M. (2009). An Introduction to MultiAgent Systems. John Wiley & Sons, 2 edition.
Xu, J., Wang, H., Niu, Z., Wu, H., and Che, W. (2020). Knowledge graph grounded goal planning for open-domain conversation generation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):9338–9345.
Yaw, C. T., Yap, K. S., Wong, S. Y., Yap, H. J., and Paw, J. K. S. (2020). Enhancement of neural network based multi agent system for classification and regression in energy system. IEEE Access, 8:163026–163043.
Zellers, R., Holtzman, A., Peters, M., Mottaghi, R., Kembhavi, A., Farhadi, A., and Choi, Y. (2021). Piglet: Language grounding through neuro-symbolic interaction in a 3d world. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), page 2040–2050. Association for Computational Linguistics.
Zhang, H., Du, W., Shan, J., Zhou, Q., Du, Y., Tenenbaum, J. B., Shu, T., and Gan, C. (2024). Building cooperative embodied agents modularly with large language models.
Zhang, L., Ford, V., Chen, Z., and Chen, J. (2025). Automatic building energy model development and debugging using large language models agentic workflow. Energy and Buildings, 327:115116.
Publicado
19/10/2026
Como Citar
MONTEIRO, Guilherme; ALVES, Gleifer V.; BORGES, André P.; CARDOSO, Rafael C..
From Cognition to Simulation: A Systematic Mapping of Visualisation and Interaction in Multi-Agent System. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 20. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 158-169.
ISSN 2326-5434.
DOI: https://doi.org/10.5753/wesaac.2026.31622.
