Protocol Emergence under Bandwidth Limits in Cooperative Language-Agent Teams
DOI:
https://doi.org/10.66238/ijrss.v6i2.123Keywords:
Multi-Agent Systems, Emergent Communication, Large Language Models, Bandwidth Constraints, Information TheoryAbstract
The rapid advancement of large language models has facilitated the development of multi-agent systems capable of executing complex, collaborative tasks. However, as these systems scale, the communication overhead between language agents becomes a significant bottleneck. This paper investigates the phenomenon of protocol emergence when cooperative language-agent teams are subjected to stringent bandwidth constraints. By artificially limiting the token budget available for inter-agent communication, we observe how agents adapt their natural language discourse into highly compressed, task-specific protocols. Drawing upon principles from information theory, multi-agent reinforcement learning, and computational linguistics, this study systematically analyzes the structural, semantic, and pragmatic shifts that occur in agent-to-agent communication channels. We design a cooperative referential and planning environment where agent pairs must coordinate to achieve shared goals while minimizing message length. Our findings indicate that agents transition from verbose natural language to a dense, jargon-like syntax, prioritizing informational entropy over grammatical correctness. This adaptation preserves task performance while significantly reducing computational and communication costs. The research provides critical insights into the fundamental mechanics of artificial communication, suggesting that bandwidth limitations can serve as a catalyst for the evolution of efficient, autonomous protocols in distributed artificial intelligence systems.
References
1. Zhao, R., Tang, J., Zeng, W., Chen, Z., & Zhao, X. (2024, October). Zero-shot knowledge graph question generation via multi-agent llms and small models synthesis. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (pp. 3341-3351).
2. Huang, Y., Thede, L., Mancini, M., Xu, W., & Akata, Z. (2025, September). Investigating structural pruning and recovery techniques for compressing multimodal large language models: An empirical study. In DAGM german conference on pattern recognition (pp. 320-336). Cham: Springer Nature Switzerland.
3. Mo, Z. A Study on Chinese-English Bilingual Question Answering Systems Using Cross-Lingual Pre-Trained Models. October 2025. Image Processing, Electronics and Computers, DOI, 10.
4. Yu, R., Wang, Y., Jiao, X., Zhang, Y., & Kwok, J. T. (2024). Direct alignment of language models via quality-aware self-refinement. arXiv preprint arXiv:2405.21040.
5. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.
6. Sang, Y. (2025, October). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1177-1180). IEEE.
7. Tang, J., Wang, Z., Gong, Z., Yu, J., Zhu, X., & Yin, J. (2025, April). Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 25246-25254).
8. Tang, J., Yang, Y., Yu, J., Wang, Z. X., Liang, H., Yao, L., & Yin, J. (2025, November). Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 7644-7662).
9. Zhang, Y., Zhao, M., Zhang, Y., & Cheung, Y. M. (2025). Trending applications of large language models: A user perspective survey. IEEE Transactions on Artificial Intelligence.
10. Su, Yiyun, et al. "Agentic-SQL Taxonomy: A Survey of Autonomous and Interactive Text-to-SQL with LLMs." (2026).
11. Jiang, J., Yang, P., Zhang, R., & Liu, F. (2026, July). Towards efficient large language model serving: A survey on system-aware kv cache optimization. In Findings of the Association for Computational Linguistics: ACL 2026 (pp. 38450-38476).
12. Cao, Y., Jing, L., Wang, Y., Shi, D., Yu, C., & Xing, J. (2026, June). Dual-Pathway Diffusion for Hand Correction in Synthetic Portraits: Global Context Aware and Local Structure Refinement. In Proceedings of the 2026 International Conference on Multimedia Retrieval (pp. 1899-1907).
13. Zhu, D., Xie, C., Zhang, H., Wei, Z., Wang, Z., Shi, J., ... & Xie, Q. (2026). Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset. arXiv preprint arXiv:2608.26109.
14. Qiu, Z., Lyu, H., Xiong, W., & Luo, J. (2025). Can llms simulate social media engagement? a study on action-guided response generation. arXiv preprint arXiv:2502.12073.
15. Qiu, Z., Qiu, K., Lyu, H., Xiong, W., & Luo, J. (2024, December). Semantics preserving emoji recommendation with large language models. In 2024 IEEE International Conference on Big Data (BigData) (pp. 7131-7140). IEEE.
16. Tang, J., Yuan, X., Liu, J., Yu, J., Dong, X., Chen, L., ... & Yin, J. (2026). SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2604.20146.
17. Fan, D., Liu, M., Shao, Y., Yang, L., Liu, Y., Zhang, Y., ... & Wang, Z. (2025). Domain-specific large language model for maintenance decision-making on wind farms by labeled-data-supervised fine-tuning. Engineering.
18. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692.
19. Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems.
20. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems.
21. Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020). BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of ACL.
22. Li, Q., Ye, Q., Zhang, N., Zhang, W., & Hu, F. (2025). Digital-twin-enabled industrial IoT: Vision, framework, and future directions. IEEE Wireless Communications, 32(6), 173-181.
23. Li, S. (2025). Momentum, volume and investor sentiment study for us technology sector stocks—A hidden markov model based principal component analysis. PloS one, 20(9), e0331658.
24. 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.
25. 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.
26. Liang, R., Xu, S., Xie, C., Chen, J., Ren, F., Yang, S., & Yabe, T. (2026). Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency. Advances in Neural Information Processing Systems, 38, 99445-99471.
27. Li, S. (2024). Machine Learning in Credit Risk Forecasting — — A Survey on Credit Risk Exposure. Accounting and Finance Research, 13(2), 107-107.
28. Zhao, J., Zhang, C., Qin, M., & Yang, P. (2025). QuantFactor REINFORCE: mining steady formulaic alpha factors with variance-bounded REINFORCE. IEEE Transactions on Signal Processing, 73, 2448-2463.
29. Sha, L., Wang, Y., Meng, P., Deng, Y., Chen, T., Zhang, X., ... & Xu, Q. (2025). Pharmacological inhibition of PSPH reduces serine levels and epileptic seizures. Nature Chemical Biology, 21(11), 1742-1753.
30. 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.
31. Peng, Y., & Li, H. (2023). Benthic foraminiferal morphogroups at the end-Guadalupian extinction in eastern Sichuan Basin, China. Palaeogeography, Palaeoclimatology, Palaeoecology, 618, 111522.
32. Yao, J., Yao, C., Chen, Y., Liu, X., Huang, D., & Chu, W. (2026, April). Explainable AI Enhanced Traffic Forecasting for Proactive Autonomous Vehicle Routing. In 2026 IEEE Conference on Technologies for Sustainability (SusTech) (pp. 1-7). IEEE.
33. Tao, J., Lyu, R., & Cao, X. (2026). A Deep Learning-Based Automated Content Moderation Framework for Online Platforms.Future-Adaptive Intelligence and Lifelong Systems,1(1).
34. Ling, C., & Wang, Y. (2025). TLFQC: A High-compatible R Shiny based Platform for Automated and Codeless TLFs Generation and Validation. In PharmaSUG 2025 conference proceedings.
35. Dong, X., Ramachandra, N., Habib, S., Heitmann, K., Buehlmann, M., & Madireddy, S. (2021). Physical Benchmarking for AI-Generated Cosmic Web. arXiv preprint arXiv:2112.05681.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Greta Krause
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.
