Elamur Research⌕
☰
home / papers / 2026 / Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval

Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval

Paper · 2026 · Joaquin Polonuer, Lucas Vittor, Iñaki Arango et al.

Summary

Retrieving evidence from knowledge graphs (KGs) for language model queries requires two things at once. The retriever must search widely enough to land in the right part of the graph, and it must follow relational links over several hops. Similarity-based retrievers cover the graph but rarely reason over its structure. Traversal-based agents depend on picking good starting entities, so they break down when queries involve many entities or relations.

The authors propose ARK (Adaptive Retriever of Knowledge), a training-free agent that lets an LLM decide how to balance breadth and depth. It uses only two tools:

  • BM25-style lexical search over node descriptors across the whole graph;
  • one-hop neighbor expansion, which can be chained into multi-hop paths.

ARK needs no seed selection, fixed hop limit or retrieval training. Global search stays available at every step, so the agent can recover from a bad starting point.

On the STaRK benchmark, ARK outperforms both retrieval-based and agent-based training-free baselines. Its behaviour also transfers to a small open model through label-free imitation of its trajectories. This makes adaptive KG retrieval cheaper and more portable across domains.

Key points

  • On STaRK (AMAZON, MAG, PRIME), ARK reaches an average Hit@1 of 59.1% and an average MRR of 67.4. Compared with training-free baselines, this is up to 31.4% higher average Hit@1 and up to 28.0% higher MRR.
  • The agent adapts its tool use to the query: it relies on global search for text-heavy queries and on neighborhood exploration for relation-heavy ones.
  • Distilling ARK's trajectories into Qwen3-8B, without any labels, raises Hit@1 over the base 8B model by +7.0 on AMAZON, +26.6 on MAG and +13.5 on PRIME. The distilled model keeps up to 98.5% of the teacher's Hit@1.
  • Error analysis shows two failure patterns: runs that never expand neighborhoods, and runs that expand far too often. Successful runs seldom exceed ten neighborhood calls.
  • Limitations include higher latency, dependence on a large proprietary LLM for the best results, and vocabulary mismatch in lexical search. Code is available at github.com/mims-harvard/ark.

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

🎓University of OxfordOxford · United Kingdom104 works · 157,183 citations🎓Harvard UniversityCambridge · United States112 works · 42,023 citations🎓Universidad de Buenos AiresBuenos Aires · Argentina8 works · 447 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Information retrieval & search · 473 worksKnowledge graphs & ontologies · 192 works

Cite

Cite as Joaquin Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori, David A. Clifton, Luciano Del Corro and Marinka Zitnik. 2026. Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.714

@inproceedings{polonuer2026autonomous,
  title = {{Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval}},
  author = {Joaquin Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori, David A. Clifton, Luciano {Del Corro} and Marinka Zitnik},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.714},
  url = {https://doi.org/10.18653/v1/2026.acl-long.714}
}

References

68 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, and Caiming Xiong. 2020. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering. arXiv preprint. ArXiv:1911.10470 [cs].
  2. Emmanuel Bengio, Moksh Jain, Maksym Korablyov, Doina Precup, and Yoshua Bengio. 2021. Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation. arXiv preprint. Version Number: 2. find
  3. Payal Chandak, Kexin Huang, and Marinka Zitnik. 2023. Building a knowledge graph to enable precision medicine. Scientific Data, 10(1):67. Publisher: Nature Publishing Group.
  4. Jialin Chen, Houyu Zhang, Seongjun Yun, Alejandro Mottini, Rex Ying, Xiang Song, Vassilis N. Ioannidis, Zheng Li, and Qingjun Cui. 2025. GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 163… find
  5. Gordon V. Cormack, Charles L A Clarke, and Stefan Buettcher. 2009. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, SIGIR ’09, pages 758–759, New York…
  6. Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum. 2018. Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. arXiv preprint. ArXiv:1711.05851 [cs]. find
  7. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv preprint. ArXiv:2404.16130 [cs]. find
  8. Ronald Fagin, Ravi Kumar, and D. Sivakumar. 2003. Efficient similarity search and classification via rank aggregation. In Proceedings of the 2003 ACM SIG-MOD international conference on Management of data, SIGMOD ’03, pages 301–312, New York, NY, USA. Association for Computing Machinery. find
  9. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: retrieval-augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of ICML’20, pages 3929–3938. JMLR.org.
  10. Ruining He and Julian McAuley. 2016. Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering. In Proceedings of the 25th International Conference on World Wide Web, WWW ’16, pages 507–517, Republic and Canton of Geneva, CHE. International World Wide Web… find
  11. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering. arXiv preprint. ArXiv:2402.07630 [cs].
  12. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint. ArXiv:1503.02531 [stat].
  13. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arXiv preprint. ArXiv:2106.09685 [cs].
  14. Yikuan Hu, Jifeng Zhu, Lanrui Tang, and Chen Huang. 2025a. ReMindRAG: low-cost LLM-guided knowledge graph traversal for efficient RAG. NeurIPS. find
  15. Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2025b. GRAG: Graph Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4145–4157, Albuquerque, New Mexico. Association for Computational Linguistics. find
  16. Mathew Huerta-Enochian and Seung Yong Ko. 2024. Instruction Fine-Tuning: Does Prompt Loss Matter? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22771–22795, Miami, Florida, USA. Association for Computational Linguistics. find
  17. Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 874–880, Online. Association for Computa…
  18. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2025. Database-augmented query representation for information retrieval. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 16622– 16644. find
  19. Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 2025. Voting or Consensus? Decision-Making in Multi-Agent Debate. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11640–11671. ArXiv:2502.19130 [cs]. find
  20. Minki Kang, Jongwon Jeong, Seanie Lee, Jaewoong Cho, and Sung Ju Hwang. 2025. Distilling LLM Agent into Small Models with Retrieval and Code Tools. arXiv preprint. ArXiv:2505.17612 [cs].
  21. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769– 6781, Onl…
  22. Youmin Ko, Sungjong Seo, and Hyunjoon Kim. 2025. Cooperative retrieval-augmented generation for question answering: Mutual information exchange and ranking by contrasting layers. In NeurIPS. find
  23. Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, and Christos Faloutsos. 2025. HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases. In Proceedings of the 63rd Annual Meeting of the Association for Computa… find
  24. Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, and Yu Wang. 2025. Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases. In Findings of the Association for Computational Linguistics: ACL 2025, pages 18306– 18… find
  25. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the 34th Internation…
  26. Millicent Li, Tongfei Chen, Benjamin Van Durme, and Patrick Xia. 2025a. Multi-Field Adaptive Retrieval. arXiv preprint. ArXiv:2410.20056 [cs]. — [arXiv:2410.20056](https://arxiv.org/abs/2410.20056) find
  27. Mufei Li, Siqi Miao, and Pan Li. 2025b. Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation. arXiv preprint. ArXiv:2410.20724 [cs]. — [arXiv:2410.20724](https://arxiv.org/abs/2410.20724) find
  28. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Ye Qi, and Zhicheng Dou. 2025c. RetroLLM: Empowering large language models to retrieve fine-grained evidence within generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  29. Runxuan Liu, Luobei Luobei, Jiaqi Li, Baoxin Wang, Ming Liu, Dayong Wu, Shijin Wang, and Bing Qin. 2025. Ontology-guided reverse thinking makes large language models stronger on knowledge graph question answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguis…
  30. Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. arXiv preprint. ArXiv:1711.05101 [cs]. find
  31. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. arXiv preprint. ArXiv:2310.01061 [cs]. find
  32. Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, and Jian Guo. 2025. Think-on-graph 2.0: Deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation. ICLR. find
  33. Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. 2008. Introduction to information retrieval. Cambridge university press, Cambridge. find
  34. Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, and Aram Galstyan. 2024. Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs. In Proceedings of the 62nd Annual Meeting of the A… find
  35. Costas Mavromatis and George Karypis. 2025. GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16682–16699, Vienna, Austria. Association for Computational Linguistics. find
  36. Julian McAuley, Rahul Pandey, and Jure Leskovec. 2015. Inferring Networks of Substitutable and Complementary Products. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’15, pages 785–794, New York, NY, USA. Association for Computing Machinery… find
  37. Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2025. Generative Representational Instruction Tuning. arXiv preprint. ArXiv:2402.09906 [cs].
  38. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Train…
  39. Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2025. Investigating the factual knowledge boundary of large language models with retrieval augmentation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3697–3…
  40. Stephen Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr., 3(4):333–389. find
  41. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv preprint. ArXiv:2302.04761 [cs].
  42. Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, and Aldo Lipani. 2024. Instruction Tuning With Loss Over Instructions. arXiv preprint. ArXiv:2405.14394 [cs]. — [arXiv:2405.14394](https://arxiv.org/abs/2405.14394) find
  43. Haitian Sun, Tania Bedrax-Weiss, and William Cohen. 2019. PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lang… find
  44. Jia Ao Sun, Hao Yu, Fabrizio Gotti, Fengran Mo, Yihong Wu, Yuchen Hui, and Jian-Yun Nie. 2025. Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs. arXiv preprint. ArXiv:2510.08825 [cs]. — [arXiv:2510.08825](https://arxiv.org/abs/2510.08825) find
  45. 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. arXiv preprint. ArXiv:2307.07697 [cs]. find
  46. Prakhar Verma, Sukruta Prakash Midigeshi, Gaurav Sinha, Arno Solin, Nagarajan Natarajan, and Amit Sharma. 2024. Plan* RAG: Efficient test-time planning for retrieval augmented generation. arXiv:2410.20753. — [arXiv:2410.20753](https://arxiv.org/abs/2410.20753) find
  47. Junhong Wan, Tao Yu, Kunyu Jiang, Yao Fu, Weihao Jiang, and Jiang Zhu. 2025. Digest the knowledge: Large language models empowered message passing for knowledge graph question answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers… find
  48. Cunxiang Wang, Xiaoze Liu, Yuanhao Yue, Qipeng Guo, Xiangkun Hu, Xiangru Tang, Tianhang Zhang, Cheng Jiayang, Yunzhi Yao, Xuming Hu, and 1 others. 2025a. Survey on factuality in large language models. ACM Computing Surveys, 58(1):1–37. find
  49. Kuansan Wang, Zhihong Shen, Chiyuan Huang, Chieh-Han Wu, Yuxiao Dong, and Anshul Kanakia. 2020. Microsoft Academic Graph: When experts are not enough. Quantitative Science Studies, 1(1):396–413. find
  50. Liang Wang, Haonan Chen, Nan Yang, Xiaolong Huang, Zhicheng Dou, and Furu Wei. 2025b. Chain-of-retrieval augmented generation. In NeurIPS. find
  51. Usage via Contrastive Reasoning. arXiv preprint. ArXiv:2406.11200 [cs]. find
  52. Shirley Wu, Shiyu Zhao, Michihiro Yasunaga, Kexin Huang, Kaidi Cao, Qian Huang, Vassiiis N. Ioannidis, Karthik Suhhian, James Zou, and Jure Leskovec. 2024b. STARK: benchmarking LLM retrieval on textual and relational knowledge bases. In Proceedings of the 38th International Conference on Neural Info… find
  53. Sirui Xia, Xintao Wang, Jiaqing Liang, Yifei Zhang, Weikang Zhou, Jiaji Deng, Fei Yu, and Yanghua Xiao. 2025a. Ground every sentence: Improving retrieval-augmented llms with interleaved reference-claim generation. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 969– 9… find
  54. Yu Xia, Junda Wu, Sungchul Kim, Tong Yu, Ryan A. Rossi, Haoliang Wang, and Julian McAuley. 2025b. Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval. arXiv preprint. ArXiv:2410.13765 [cs]. find
  55. Wenhan Xiong, Thien Hoang, and William Yang Wang. 2017. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 564–573, Copenhagen, Denmark. Association for Computational Linguistics. find
  56. Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen, Tianyi Zhang, Shijie Zhang, Wei Qiang Zhang, Yongfeng Huang, Haixin Duan, and 1 others. 2026. Explore-on-graph: Incentivizing autonomous exploration of large language models on knowledge graphs with path-refined reward modeling. ICLR. find
  57. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025a. Qwen3 Technical Report. arXiv preprint. ArXiv:2505.09388…
  58. Shuai Wang and Yinan Yu. 2026. KG-Hopper: empowering compact open llms with knowledge graph reasoning via reinforcement learning. IJCNN. find
  59. Cehao Yang, Xiaojun Wu, Xueyuan Lin, Chengjin Xu, Xuhui Jiang, Yuanliang Sun, Jia Li, Hui Xiong, and Jian Guo. 2025b. GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation. arXiv preprint. ArXiv:2509.22009 [cs]. — [arXiv:2509.22009](https://arxiv.org/abs/2509.22009) find
  60. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. arXiv preprint. ArXiv:2203.11171 [cs].
  61. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. arXiv preprint. ArXiv:2210.03629 [cs].
  62. Shirley Wu, Shiyu Zhao, Qian Huang, Kexin Huang, Michihiro Yasunaga, Kaidi Cao, Vassilis N. Ioannidis, Karthik Subbian, Jure Leskovec, and James Zou. 2024a. AvaTaR: Optimizing LLM Agents for Tool Sijia Yao, Pengcheng Huang, Zhenghao Liu, Yu Gu, Yukun Yan, Shi Yu, and Ge Yu. 2025. ExpandR: teaching d… find
  63. Junchi Yu, Yujie Liu, Jindong Gu, Philip Torr, Can Knowledge-and Dongzhan Zhou. 2025. Graph-based Retrieval Augmented Generation Really Retrieve What You Need? arXiv preprint. ArXiv:2510.16582 [cs]. — [arXiv:2510.16582](https://arxiv.org/abs/2510.16582) find
  64. Shuo Zhang, Liangming Pan, Junzhou Zhao, and William Yang Wang. 2024. The knowledge alignment problem: Bridging human and external knowledge for large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2025–2038. find
  65. Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, and Jundong Li. 2025. CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16088–16101, S… find
  66. Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, and Wei Hu. 2025a. Mitigating lost-in-retrieval problems in retrieval augmented multi-hop question answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 22362–22375, Vienna…
  67. Xiangrong Zhu, Yuexiang Xie, Yi Liu, Yaliang Li, and Wei Hu. 2025b. Knowledge Graph-Guided Retrieval Augmented Generation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers… find
  68. Method Hit@1 AMAZON Hit@5 R@20 MRR Hit@1 MAG Hit@5 R@20 MRR Hit@1 PRIME Hit@5 R@20 MRR GPT-4o GPT-4.1 GPT-5.2 Qwen3-4B Qwen3-4B-600 Qwen3-4B-6000 Qwen3-8B Qwen3-8B-600 Qwen3-8B-6000 55.13 55.82 56.12 45.69 50.10 54.46 47.95 50.06 54.99 76.37 75.80 77.76 67.46 71.26 74.66 70.03 70.07 74.35 64.29 64.7… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/polonuer-2026-autonomous-knowledge-graph-exploration-adaptive/