Emergent Symbolic Communication for Coordinated Reasoning in Partially Observable Large Language Model Agent Systems
DOI:
https://doi.org/10.66238/ijrss.v6i2.118Keywords:
Large Language Models, Multi-Agent Systems, Symbolic Reasoning, Emergent Communication, Partial ObservabilityAbstract
The deployment of large language models as autonomous agents has demonstrated remarkable capabilities in natural language understanding, reasoning, and tool use. However, when multiple such agents operate in partially observable environments, their ability to coordinate effectively is often bottlenecked by the inefficiencies of standard natural language communication and the cognitive load of processing high-dimensional contextual information. This paper investigates the phenomenon of emergent symbolic communication among large language model agents tasked with cooperative problem-solving under strict partial observability. We propose a novel cognitive architecture that incentivizes agents to compress complex environmental states and reasoning trajectories into discrete, compositional symbolic representations. Through extensive empirical analysis across decentralized decision-making tasks, we demonstrate that agents can autonomously develop a highly efficient, context-dependent symbolic vocabulary that significantly outperforms standard natural language protocols in both transmission efficiency and coordination success rates. Furthermore, we provide a rigorous theoretical framework grounded in information theory to model the symbolic compression process. Our findings reveal that the emergent language exhibits structural properties akin to natural languages, such as Zipfian distribution and compositionality, while being heavily optimized for the specific constraints of the environment. This research advances the understanding of multi-agent coordination, offering a scalable methodology for deploying robust, bandwidth-efficient agent swarms in complex, real-world scenarios.
References
1. Liu, H., Lin, R., Kashyap, A., Cui, H., Henao, R., Fetahu, B., & Yin, B. (2026). Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR. arXiv preprint arXiv:2606.07995.
2. Li, Y., Yang, Z., Huang, Y., Liu, X., & Qi, G. (2026, March). C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 38, pp. 31834-31842).
3. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2025). UAV-relay-aided secure maritime networks coexisting with satellite networks: robust beamforming and trajectory optimization. IEEE Transactions on Wireless Communications.
4. Yao, Y., Zhang, J., Miao, P., Zhang, L., Chen, G., Shu, F., & Wong, K. K. (2025). Hybrid RIS-enhanced ISAC secure systems: Joint optimization in the presence of an extended target. IEEE Transactions on Communications.
5. Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
6. Xu, X., Tu, W., & Yang, Y. (2025). Efficient audio–visual information fusion using encoding pace synchronization for Audio–Visual Speech Separation. Information Fusion, 115, 102749.
7. Wang, X., Suzuki, Y., Li, C. M., & Tanaka, S. (2025, June). Micropatterned PDMS damping layer integration to enhance the fidelity of piezoelectric MEMS speakers without SPL penalty. In 2025 23rd International Conference on Solid-State Sensors, Actuators and Microsystems (Transducers) (pp. 455-458). IEEE.
8. Li, Y., Bai, X., Liu, S., & Zhang, L. (2026). RepBench: Compiling benchmarks into capability representations for large language models. arXiv. https://arxiv.org/abs/2607.28008
9. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning.arXiv preprint arXiv:2606.29354.
10. 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).
11. Wei, W. D., Fang, H. B., Liu, Y. D., Shi, J. X., Kwok, J., & Li, Y. F. (2026). Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm. arXiv preprint arXiv:2605.01255.
12. Zhu, R., Jiang, X., Wu, J., Ma, Z., Song, J., Bai, F., ... & He, C. (2025, April). GRAIT: gradient-driven refusal-aware instruction tuning for effective hallucination mitigation. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 4006-4021).
13. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations. In Proceedings of NAACL-HLT.
14. Vinyals, O., Fortunato, M., & Jaitly, N. (2015). Pointer networks. In Advances in Neural Information Processing Systems.
15. Guo, J., Chen, X., Xia, Q., Wang, Z., Ou, J., Qin, L., ... & Tian, W. (2025, July). HASH-RAG: bridging deep hashing with retriever for efficient, fine retrieval and augmented generation. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 26847-26858).
16. Zhang, W., & Pei, S. (2026). Predictive prefetching for retrieval-augmented generation. Proceedings of Machine Learning Research. The Forty-third International Conference on Machine Learning, ICML 2026. https://par.nsf.gov/biblio/10686293
17. 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.
18. Yang Y, Yang X, Jiang Y, et al. GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems[J]. arXiv preprint arXiv:2602.15776, 2026.
19. Xie, Z., Liao, R., Wang, Z., Chen, C., Hua, X. S., & Luo, X. (2026, July). GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 10281-10293).
20. 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.
21. Xu, X., Tu, W., Yang, Y., Li, J., & Zhang, Y. (2025). Interactive target positive and negative features modeling for monaural speech enhancement.IEEE Transactions on Audio, Speech and Language Processing,33, 4856-4869.
22. 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).
23. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.
24. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems.
25. Guo, J., Shuang, K., Zhang, K., Liu, Y., Li, J., & Wang, Z. (2023, June). Learning to imagine: distillation-based interactive context exploitation for dialogue state tracking. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 11, pp. 12845-12853).
26. Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). BLEU: A method for automatic evaluation of machine translation. In Proceedings of ACL.
27. Han, C., Ma, Y., Tan, J., Zheng, W., & Tang, X. (2026, March). Beyond detection: Exploring evidence-based multi-agent debate for misinformation intervention and persuasion. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 45, pp. 38542-38550).
28. 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.
29. Wang, H., Xu, Q., Liu, C., Wu, J., Lin, F., & Chen, W. (2026, April). Emergent hierarchical reasoning in llms through reinforcement learning. In International Conference on Learning Representations (Vol. 2026, pp. 74519-74543).
30. Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.
31. Qian, B., Guo, J., Wang, Q., & Shuang, K. (2025). From local verification to global reasoning: Exploiting slot-accompanying update for improved slot selection. Knowledge-Based Systems, 319, 113521.
32. Sang, Y. (2025, August). Robustness of fine-tuned llms under noisy retrieval inputs. In 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) (pp. 417-420). IEEE.
33. Yao, Y., Zhu, Z., Miao, P., Cheng, X., Shu, F., & Wang, J. (2025). Optimizing hybrid RIS-aided ISAC systems in V2X networks: A deep reinforcement learning method for anti-eavesdropping techniques. IEEE Transactions on Vehicular Technology, 74 (6), 9224-9239.
34. 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.
35. Zhu, R., Ma, Z., Wu, J., Gao, J., Wang, J., Lin, D., & He, C. (2025, April). Utilize the flow before stepping into the same river twice: Certainty represented knowledge flow for refusal-aware instruction tuning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 26157-26165).
36. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement generative adversarial network. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7308-7311). IEEE.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Wen Tang, Gary Hung
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.
