Agent Coordination Through Emergent Symbolic Communication Under Bandwidth Limits
DOI:
https://doi.org/10.66238/ijrss.v6i2.136Keywords:
Multi-Agent Systems, Emergent Communication, Bandwidth Limits, Reinforcement LearningAbstract
The capacity for autonomous agents to coordinate their actions in complex environments is increasingly contingent upon their ability to communicate effectively. However, in many practical applications, such as distributed robotic swarms and remote sensor networks, communication channels are severely constrained by physical bandwidth limitations. This paper investigates the phenomenon of emergent symbolic communication among learning agents operating under strict bandwidth constraints. By framing the coordination problem within a multi-agent reinforcement learning paradigm, we explore how discrete, low-dimensional symbolic tokens can evolve to encapsulate high-dimensional environmental observations and strategic intentions. The study systematically evaluates the impact of varying channel capacities on the structural properties of the emergent lexicon and the consequent coordination performance of the agent collective. Through comprehensive theoretical analysis and simulated experimental environments, we demonstrate that optimal bandwidth restriction serves as a regularization mechanism, forcing agents to develop highly compositional and generalizable communication protocols. These emergent languages not only reduce the communication overhead but also exhibit structural similarities to natural language, specifically in terms of synonymy, polysemy, and context-dependent disambiguation. The findings provide critical insights into the design of efficient, robust multi-agent systems and contribute to the broader understanding of language evolution in artificial intelligence.
References
Li, B., Zhang, R., Liang, H., Zhang, J., Zhang, J., Chen, X., ... & Wang, J. (2026). Interagent: Physics-based multi-agent command execution via diffusion on interaction graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15253-15265).
Li, Q., Feng, Y., Wen, M., Wen, J., Alexandropoulos, G. C., Basar, E., & Poor, H. V. (2024). Cooperative backscatter communications with reconfigurable intelligent surfaces: An APSK approach. IEEE Transactions on Wireless Communications, 23(11), 16218-16233.
Liu, J., Nazeri, A., Zhao, C., Abuhdima, E., Comert, G., Huang, C. T., & Pisu, P. (2022, October). Investigation of 5G and 4G V2V communication channel performance under severe weather. In 2022 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE) (pp. 12-17). IEEE.
Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
He, S., Wang, R., Liao, Q., Song, L., & Chen, Y. (2026, April). A Multi-Dimensional Regulatory Technology Model for Trusted AI Systems in Government Domains. In Proceedings of the 3rd International Conference on Machine Intelligence and Digital Applications (pp. 2045-2051).
Wang, X., Zhang, L., Pu, H., Li, H., & Qureshi, A. H. (2026, April). Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form. In International Conference on Learning Representations (Vol. 2026, pp. 12422-12448).
Jiang, C., Li, L., & Tao, Z. StreamSense: A Content-and Resource-Aware Edge Agent for Adaptive Bitrate Streaming. In Grounding Language Models: Learning Faithfully and Efficiently@ EMNLP 2026.
Sun, L., Zhang, Z., Ji, P., Wen, J., Su, S., & Yu, P. S. (2019, December). DNA: Dynamic social network alignment. In 2019 IEEE International Conference on Big Data (Big Data) (pp. 1224-1231). IEEE.
Xiao, W., Tan, Q., Chen, M., Yao, Y., & Shu, F. (2026). Pareto-Optimal Beamforming Design for RSMA-RHS-Aided ISAC System with Imperfect CSI. IEEE Transactions on Vehicular Technology.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems.
Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
Zhang, Q., Gao, W., Liu, C., Yao, Y., Yan, S., Shu, F., & Jin, S. (2025). Covert transmission for active RIS-aided full-duplex UAV integrated sensing, communication, and computation systems. IEEE Journal on Selected Areas in Communications.
Hu, Y., Yang, Z., Zhao, C., & Ji, W. (2026, May). Adaptive guidance semantically enhanced via multimodal llm for edge-cloud object detection. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 12962-12966). IEEE.
Yang, Y., Yang, X., Jiang, Y., Mu, N., Hu, H., Xie, R., ... & Xu, B. (2026). GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems. arXiv preprint arXiv:2602.15776.
Kim, E. H., Huang, H., Wang, Z., Duan, H., Fu, Z., & Pedrycz, W. (2026). Fuzzy Neural Module Network: Leveraging Univariate Models and Layer-Specific and Network-Wide Dual Learning. IEEE Transactions on Cybernetics.
Zhao, J., Zhang, C., Wang, C., & Yang, P. (2025). Learning from expert factors: Trajectory-level reward shaping for formulaic alpha mining. arXiv preprint arXiv:2507.20263.
Wei, M., Li, R., Wang, L., Chang, Z., Xu, L., & Han, Z. (2026). Toward Adaptive Tracking and Communication via an Airborne Maneuverable Bi-Static ISAC System. IEEE Transactions on Vehicular Technology.
Yang, Z., Hu, D., Guo, Q., Zuo, L., & Ji, W. (2023). Visual E 2 C: AI-driven visual end-edge-cloud architecture for 6G in low-carbon smart cities. IEEE Wireless Communications, 30(3), 204-210.
Xiaoteng Ma, Yiqin Yang, Hao Hu, Qihan Liu, Jun Yang, Chongjie Zhang, Qianchuan Zhao, and Bin Liang. Offline reinforcement learning with value-based episodic memory. arXiv preprint arXiv:2110.09796, 2021b.
Wang, X., Zhang, L., Pu, H., Qureshi, A. H., & Li, H. (2026, April). Continuous-time value iteration for multi-agent reinforcement learning. In International Conference on Learning Representations (Vol. 2026, pp. 93980-93999).
Meng, X., & Lin, J. (2026). AURA-Trace: Auditable Provenance-Aware Synthetic Release of Campus IoT Time Series for Privacy-Preserving AI4Science. IEEE Internet of Things Journal.
Feng, Y., Li, Q., Chen, Y., Wu, Q., & Wen, M. (2024). RIS-aided symbiotic radio: A number and phase modulation approach. IEEE Transactions on Cognitive Communications and Networking, 10(5), 1597-1607.
Li, X., Chen, W., Liu, X., & Ren, M. (2015). A high-order sigma-delta accelerometer interface circuit.IEICE Electronics Express,12(2), 20141035-20141035.
Wei, X., Li, R., Chen, Y., Xu, L., Wang, L., & Han, Z. (2026). Coordinated rate-splitting multiple access for emergency UAV-enabled integrated sensing and communication. IEEE Transactions on Cognitive Communications and Networking.
Yao, Y., Shu, F., Li, Z., Cheng, X., & Wu, L. (2023). Secure transmission scheme based on joint radar and communication in mobile vehicular networks. IEEE transactions on intelligent transportation systems, 24 (9), 10027-10037.
Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning. arXiv preprint arXiv:2606.29354.
Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., et al. (2022). Do as I can, not as I say: Grounding language in robotic affordances. In Proceedings of the Conference on Robot Learning.
Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., Dabis, J., Finn, C., et al. (2023). RT-1: Robotics transformer for real-world control at scale. In Proceedings of Robotics: Science and Systems.
Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Tiffany Tsz-Kit Luk, Chris Yu
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the International Journal of Research & Social Sciences are published under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Users may share and adapt the content, including for commercial purposes, provided proper credit is given to the authors and the journal.
