Synergistic AI Agents
Integrating Knowledge Graphs and Large Language Models for Scholarly Communication
DOI:
https://doi.org/10.52825/ocp.v8i.3172Keywords:
Agentic AI, Knowledge Graph, Scholarly ResearchAbstract
Agentic AI is and emerging field of artificial intelligence and it has great impact on scholarly research. Agentic AI helps to handle large volume of information from vast corpora. Currently the Agentic AI systems depends on Large Language Models (LLM) for the tasks of information retrieval and reasoning. LLMs are very effective at Natural Language Understanding and the iterative reasoning. However, there exist some inherent limitations for LLMs, which pose challenges for Agentic AI. Provenance tracking, reasoning challenges, temporal staleness and context dilution are some examples. Incorporating Knowledge Graphs (KG) along with LLMs can mitigate these challenges, and can support deeps search in Agentic AI.
In this work, we are exploring the aspects of how KG is well suited for addressing these challenges, and how KG can complement LLMs in Agentic AI for scholarly research. Furthermore, we investigate the problem of frequency bias inherent in LLMs. Frequency bias distorts the outputs in LLMs by biasing towards the most frequent inputs. We examine how a KG integration can counteract this problem. Overall, through this work we aim to highlight the potential of Knowledge Graphs for Agentic AI in scholarly communication.
Downloads
References
[1] J. van den Akker, and A. Siebes, "Enriching active databases with agent technology", in International Workshop on Cooperative Information Agents, 1997, pp. 116–125.
[2] J. Bailey, M. Georgeff, D. B. Kemp, D. Kinny, and K. Ramamohanarao, "Active databases and agent systems—A comparison", in International Workshop on Rules in Database Systems, 1995, pp. 342–356.
[3] M. Y. Jaradeh, and S. Auer, "Deep Research in the Era of Agentic AI: Requirements and Limitations for Scholarly Research", in CEUR Workshop Proceedings, vol. 4065, 2025.
[4] H. Khorashadizadeh, F. Z. Amara, M. K. Ezzabady et al., "Research Trends for the Interplay between Large Language Models and Knowledge Graphs", in Proceedings of Workshops at the 50th International Conference on Very Large Data Bases, VLDB 2024, Guangzhou, China, August 26-30, 2024, 2024.
[5] M. Y. Jaradeh, A. Oelen, K. E. Farfar et al., "Open research knowledge graph: Next generation infrastructure for semantic scholarly knowledge", in Proceedings of the 10th international conference on knowledge capture, 2019, pp. 243–246.
[6] A. G. Nuzzolese, A. L. Gentile, V. Presutti, and A. Gangemi, "Conference linked data: the scholarlydata project", in International Semantic Web Conference, 2016, pp. 150–158.
[7] N. Mihindukulasooriya, S. Tiwari, D. Dobriy, F. . Nielsen, T. R. Chhetri, and A. Polleres, "Scholarly wikidata: Population and exploration of conference data in wikidata using llms", in International Conference on Knowledge Engineering and Knowledge Management, 2024, pp. 243–259.
[8] X. Zhao, M. Blum, F. Gao et al., "AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots", arXiv preprint arXiv:2508.02999, 2025.
[9] M. Gridach, J. Nanavati, K. Z. E. Abidine, L. Mendes, and C. Mack, "Agentic ai for scientific discovery: A survey of progress, challenges, and future directions", arXiv preprint arXiv:2503.08979, 2025.
[10] L. Luo, C. Yang, E. Kharlamov, and S. Pan, "Integrating Large Language Models and Knowledge Graphs for Next-level AGI", in Companion Proceedings of the ACM on Web Conference 2025, 2025, pp. 33–36.
[11] L. Yang, H. Chen, Z. Li, X. Ding, and X. Wu, "Give us the facts: Enhancing large language models with knowledge graphs for fact-aware language modeling", IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 7, pp. 3091–3110, 2024.
[12] L. Cai, Y. Kang, C. Yu, Y. Fu, H. Zhang, and Y. Zhao, "Bringing Two Worlds Together: The Convergence of Large Language Models and Knowledge Graphs", in 2024 3rd International Conference on Automation, Robotics and Computer Engineering (ICARCE), 2024, pp. 207–216.
[13] A. Amayuelas, J. Sain, S. Kaur, and C. Smiley, "Grounding LLM Reasoning with Knowledge Graphs", arXiv preprint arXiv:2502.13247, 2025.
[14] L. Cheng, Z. Wang, and M. Steedman, "LLMs are Frequency Pattern Learners in Natural Language Inference", arXiv preprint arXiv:2505.21011, 2025.
[15] T. Lebo, S. Sahoo, D. McGuinness et al., "Prov-o: The prov ontology", 2013.
[16] Y. Yao, Z. Li, and H. Zhao, "Beyond chain-of-thought, effective graph-of-thought reasoning in language models", arXiv preprint arXiv:2305.16582, 2023.
[17] J. Wei, Y. Yang, X. Zhang et al., "From ai for science to agentic science: A survey on autonomous scientific discovery", arXiv preprint arXiv:2508.14111, 2025.
[18] F. Krause, T. Weller, and H. Paulheim, "On a generalized framework for time-aware knowledge graphs", in Towards a Knowledge-Aware AI, IOS Press, 2022, pp. 69–74.
[19] Y. Zhang, R. Sun, Y. Chen, T. Pfister, R. Zhang, and S. Arik, "Chain of agents: Large language models collaborating on long-context tasks", Advances in Neural Information Processing Systems, vol. 37, pp. 132208–132237, 2024.
[20] J. Wang, R. Veugelers, and P. Stephan, "Bias against novelty in science: A cautionary tale for users of bibliometric indicators", Research Policy, vol. 46, no. 8, pp. 1416–1436, 2017.
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Bharath Chand, Sanju Tiwari, Nandana Mihindukoolasuriya, Soren Auer
This work is licensed under a Creative Commons Attribution 4.0 International License.
Accepted 2025-11-15
Published 2025-12-18