Elamur Research⌕
☰
home / papers / 2026 / Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs

Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs

Paper · 2026 · Minghan Zhang, Shu Zhao, Zhen Yang et al.

Summary

Systems that pair knowledge graphs with LLMs for question answering usually walk the graph outward from the entities named in the query. They choose each next hop by looking only at nearby neighbors. On complex multi-hop questions, this short-sighted search gets lost among hundreds of irrelevant relations, which hurts both accuracy and cost. The authors propose MIAoG. In this framework, the LLM first examines the question from several angles and writes a set of instructions that sketch possible reasoning routes and the overall goal. These instructions then steer graph exploration. After every step, an introspection module checks how well each path fits the instructions. Paths that no instruction supports are discarded, and so are instructions that no path supports. On CWQ, WebQSP and GrailQA, MIAoG reportedly reaches state-of-the-art results, with the largest gains on deep multi-hop questions. It also uses noticeably fewer tokens, LLM calls and runtime than baselines that rely on widening the search. The work suggests that planning up front can replace brute-force search expansion.

Key points

  • MIAoG works in three phases: it first produces instructions, then explores the graph under their guidance, and finally checks candidate answers through reasoning introspection. Pruning works in both directions, removing unsupported paths and unsupported instructions.
  • It is evaluated on the CWQ, WebQSP and GrailQA benchmarks, mainly with Hits@1. It is compared against ToG, StructGPT, PoG, ReKnoS and KB-BINDER.
  • Averaged over the three datasets, it uses 35.4% fewer tokens and 54.4% fewer LLM calls than ToG. Average time drops from 69.7 to 15.2. It has the lowest token usage and fastest runtime among the compared methods.
  • On CWQ split by reasoning depth, removing adaptive pruning costs only +0.5% on shallow questions but 5.2% on questions with ≥8 hops.
  • Stated limitations: the method targets single-answer questions, it adds iterative overhead, and it may scale poorly to very large KGs. Code: github.com/ahu-zmh/MIAoG.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Anhui UniversityHefei · China11 works · 7 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,894 worksReasoning · 1,685 works

Cite

Cite as Minghan Zhang, Shu Zhao, Zhen Yang, Hongsheng Wu, Yongxing Lin, Haodong Zou, Jie Chen and Zhen Duan. 2026. Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.325

@inproceedings{zhang2026thinking,
  title = {{Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs}},
  author = {Minghan Zhang, Shu Zhao, Zhen Yang, Hongsheng Wu, Yongxing Lin, Haodong Zou, Jie Chen and Zhen Duan},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.325},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.325}
}

References

31 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Thirty-Eighth AAAI Conference on… find
  2. Kurt D. Bollacker, Colin Evans, Praveen K. Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the ACM SIG-MOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-1… find
  3. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — Language Models are Few-Shot Learners
  4. Liyi Chen, Panrong Tong, Zhongming Jin, Ying Sun, Jieping Ye, and Hui Xiong. 2024. Plan-on-graph: Self-correcting adaptive planning of large language model on knowledge graphs. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, N… find
  5. Yuanheng Fang, Guoqing Chao, Wenqiang Lei, Shaobo Li, and Dianhui Chu. 2025. Cdw-cot: Clustered distance-weighted chain-of-thoughts reasoning. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 -March 4, 2025, Philadelphia, PA, USA, pages 23878– 2388… find
  6. Yu Gu, Sue Kase, Michelle Vanni, Brian M. Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021. Beyond I.I.D.: three levels of generalization for question answering on knowledge bases. In WWW ’21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pages 3477–3488. ACM / IW3… find
  7. Xinyan Guan, Yanjiang Liu, Hongyu Lin, Yaojie Lu, Ben He, Xianpei Han, and Le Sun. 2024. Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting. In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative App… find
  8. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12):248:1–248:38.
  9. Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Xin Zhao, and Ji-Rong Wen. 2023. Structgpt: A general framework for large language model to reason over structured data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 202… find
  10. Yunshi Lan and Jing Jiang. 2020. Query graph generation for answering multi-hop complex questions from knowledge bases. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 969–974. Association for Computational Linguist… find
  11. Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su, and Wenhu Chen. 2023. Few-shot in-context learning on knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023,… find
  12. Jiaxiang Liu, Tong Zhou, Yubo Chen, Kang Liu, and Jun Zhao. 2024. Enhancing large language models with pseudo- and multisource- knowledge graphs for open-ended question answering. CoRR, abs/2402.09911. — [arXiv:2402.09911](https://arxiv.org/abs/2402.09911) find
  13. OpenAI. 2023. GPT-4 technical report. abs/2303.08774.
  14. CoRR, Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. Unifying large language models and knowledge graphs: A roadmap. IEEE Trans. Knowl. Data Eng., 36(7):3580–3599.
  15. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Synthetic prompting: Generating chain-of-thought demonstrations for large language models. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedin… find
  16. Kashun Shum, Shizhe Diao, and Tong Zhang. 2023. Automatic prompt augmentation and selection with chain-of-thought from labeled data. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 12113–12139. Association for Computational Linguistics.
  17. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In The Twelfth International Conference on Learning Representations, ICLR 2024… find
  18. Alon Talmor and Jonathan Berant. 2018. The web as a knowledge-base for answering complex questions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6…
  19. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  20. Song Wang, Junhong Lin, Xiaojie Guo, Julian Shun, Jundong Li, and Yada Zhu. 2025. Reasoning of large language models over knowledge graphs with super-relations. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  21. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5,…
  22. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi…
  23. Yilin Wen, Zifeng Wang, and Jimeng Sun. 2024. Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, pag…
  24. Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, and 4 others. 2022. Unifiedskg: Uni…
  25. Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, and Weiqiang Jia. 2024. Cognitive mirage: A review of hallucinations in large language models. In Proceedings of the First International OpenKG Workshop: Large Knowledge-Enhanced Models co-locacted with The International Joint Conference on Artificial Inte… find
  26. Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2022. RNG-KBQA: generation augmented iterative ranking for knowledge base question answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ir… find
  27. Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question answering. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany,…
  28. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah D. Goodman. 2022. Star: Bootstrapping reasoning with reasoning. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  29. Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, Hao Yu, Hongning Wang, Jiadai Sun, Jiajie Zhang, Jiale Cheng, Jiayi Gui, Jie Tang, Jing Zhang, Juanzi Li, Lei Zhao, and 36 others. 2024. Chatglm: A family of large language models from GLM-130B t…
  30. Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, and Juanzi Li. 2023. FC-KBQA: A fine-to-coarse composition framework for knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: L… find
  31. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023,… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-thinking-beyond-local-multi-view/