Elamur Research⌕
☰
home / papers / 2026 / SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering

SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering

Paper · 2026 · FU Yuqing, Yimin Deng, Wanyu Wang et al.

Summary

SEARCH-R targets multi-hop question answering (MHQA), where a model must chain several facts to reach an answer. The authors identify two weaknesses in prior work. Prompt-driven question decomposition tends to drift away from the original intent. Sparse or dense retrieval rewards surface similarity and often returns redundant or unhelpful passages.

The framework has three stages:

  1. Reasoning path navigator. A sub-question decomposer based on Llama3.1-8B is trained end to end. An LLM produces many candidate decompositions, and only those yielding the correct final answer are kept for SFT. The model is then refined with PPO against a reward model that predicts answer F1.
  2. Retrieval. Dense retrieval is combined with an entity informativeness score derived from dependency parse trees, which estimates how much a document actually contributes.
  3. Answer generation. Sub-answers are produced iteratively and merged into the final answer.

Experiments on three multi-hop benchmarks show gains over the strongest baseline. The work matters because it optimises decomposition for answer correctness and judges evidence by its usefulness rather than its similarity.

Key points

  • The decomposer training data is filtered by final-answer consistency, not by logical form. Correct question-to-sub-question mappings are used for SFT. The text calls the model both 8B (abstract) and 7B (method section).
  • RL stage: a reward model is trained with MSE loss against F1 between predicted and gold answers. It then guides PPO optimisation with the standard clipped objective.
  • Retrieval module (QIR): dependency trees quantify the salience of entity tokens, since depth in the tree reflects importance. In an ablation without dense retrieval, QIR provided complementary signal, and combining both methods worked best.
  • Robustness: with one entity per sub-question masked to simulate recognition errors, the method still beat similarity-only retrieval on F1.
  • Limitations: the method depends on an external parser and NER tools, and on the quality of the LLM-generated training data. Code and data are on GitHub (Applied-Machine-Learning-Lab/ACL2026_SEARCH-R).

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

🎓Xi'an Jiaotong UniversityXi'an · China42 works · 36,431 citations🎓City University of Hong KongHong Kong · China59 works · 3,480 citations🎓Michigan State UniversityEast Lansing · United States30 works · 1,375 citations🎓Jilin UniversityChangchun · China30 works · 5,252 citations🎓Zhejiang University of TechnologyHangzhou · China8 works · 98 citations

 Fields, topics and concepts

📚 Shelves 6The 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 worksInformation Systems · 1,730 works

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1,685 worksQuestion answering · 487 worksInformation retrieval & search · 552 works

Cite

Cite as FU Yuqing, Yimin Deng, Wanyu Wang, Yuhao Wang, Yejing Wang, Hongshi Liu, Yiqi Wang, Xiao Han, Maolin Wang, Guoshuai Zhao, Yi Chang and Xiangyu Zhao. 2026. SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1953

@inproceedings{yuqing2026search,
  title = {{SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering}},
  author = {FU Yuqing, Yimin Deng, Wanyu Wang, Yuhao Wang, Yejing Wang, Hongshi Liu, Yiqi Wang, Xiao Han, Maolin Wang, Guoshuai Zhao, Yi Chang and Xiangyu Zhao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1953},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1953}
}

References

40 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Muhammad Arslan, Hussam Ghanem, Saba Munawar, and Christophe Cruz. 2024. A survey on rag with llms. Procedia computer science, 246:3781–3790. find
  2. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. The llama 3 herd of models. arXiv e-prints, pages arXiv–2407.
  3. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024a. From local to global: A graph rag approach to query-focused summarization. find
  4. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024b. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. find
  5. Zichuan Fu, Xiangyang Li, Chuhan Wu, Yichao Wang, Kuicai Dong, Xiangyu Zhao, Mengchen Zhao, Huifeng Guo, and Ruiming Tang. 2025. A unified framework for multi-domain ctr prediction via large language models. ACM Transactions on Information Systems, 43(5):1–33. find
  6. Jingtong Gao, Bo Chen, Xiangyu Zhao, Weiwen Liu, Xiangyang Li, Yichao Wang, Wanyu Wang, Huifeng Guo, and Ruiming Tang. 2025. Llm4rerank: Llm-based auto-reranking framework for recommendations. In Proceedings of the ACM on Web Conference 2025, pages 228–239. find
  7. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps. arXiv preprint arXiv:2011.01060.
  8. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2024. Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity. arXiv preprint arXiv:2403.14403.
  9. Pengyue Jia, Yiding Liu, Xiangyu Zhao, Xiaopeng Li, Changying Hao, Shuaiqiang Wang, and Dawei Yin. 2024. Mill: Mutual verification with large language models for zero-shot query expansion. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Lingui… find
  10. Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Active retrieval augmented generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992.
  11. Zhouyu Jiang, Mengshu Sun, Lei Liang, and Zhiqiang Zhang. 2025. Retrieve, summarize, plan: Advancing multi-hop question answering with an iterative approach. In Companion Proceedings of the ACM on Web Conference 2025, pages 1677–1686. find
  12. Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. Advances in Neural Information Processing Systems, 37:59532–59569.
  13. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. Search-r1: Training llms to reason and leverage search engines with reinforcement learning. Preprint, arXiv:2503.09516.
  14. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–…
  15. Yuchen Li, Hengyi Cai, Rui Kong, Xinran Chen, Jiamin Chen, Jun Yang, Haojie Zhang, Jiayi Li, Jiayi Wu, Yiqun Chen, and 1 others. 2025. Towards ai search paradigm. arXiv preprint arXiv:2506.17188. — [arXiv:2506.17188](https://arxiv.org/abs/2506.17188) find
  16. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. find
  17. Qidong Liu, Xian Wu, Wanyu Wang, Yejing Wang, Yuanshao Zhu, Xiangyu Zhao, Feng Tian, and Yefeng Zheng. 2025a. Llmemb: Large language model can be a good embedding generator for sequential recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 12183– 12191. find
  18. Qidong Liu, Xiangyu Zhao, Yuhao Wang, Yejing Wang, Zijian Zhang, Yuqi Sun, Xiang Li, Maolin Wang, Pengyue Jia, Chong Chen, and 1 others. 2025b. Large language model enhanced recommender systems: Methods, applications and trends. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery… find
  19. Amit Mishra and Sanjay Kumar Jain. 2016. A survey on question answering systems with classification. Journal of King Saud University-Computer and Information Sciences, 28(3):345–361. find
  20. Tengjun Ni, Xin Yuan, Shenghong Li, Kai Wu, Ren Ping Liu, Wei Ni, and Wenjie Zhang. 2025. Stepchain graphrag: Reasoning over knowledge graphs for multi-hop question answering. Preprint, arXiv:2510.02827. — [arXiv:2510.02827](https://arxiv.org/abs/2510.02827) find
  21. Bolanle Ojokoh and Emmanuel Adebisi. 2018. A review of question answering systems. Journal of Web Engineering, 17(8):717–758. find
  22. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. find
  23. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. arXiv preprint arXiv:2305.15294.
  24. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, and Suranga Nanayakkara. 2023. Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering. Transactions of the Association for Computational Linguistics,…
  25. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022a. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. arXiv preprint arXiv:2212.10509.
  26. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022b. musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. find
  27. Hanbing Wang, Xiaorui Liu, Wenqi Fan, Xiangyu Zhao, Venkataramana Kini, Devendra Pratap Yadav, Fei Wang, Zhen Wen, and Hui Liu. 2025. Rethinking large language model architectures for sequential recommendations. In Proceedings of the 14th International Joint Conference on Natural Language Processing… find
  28. Yuhao Wang, Xiangyu Zhao, Bo Chen, Qidong Liu, Huifeng Guo, Huanshuo Liu, Yichao Wang, Rui Zhang, and Ruiming Tang. 2023. Plate: A prompt-enhanced paradigm for multi-scenario recommendations. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Ret… find
  29. Tongzhou Wu, Yuhao Wang, Xinyu Ma, Xiuqiang He, Shuaiqiang Wang, Dawei Yin, and Xiangyu Zhao. 2026. Deepresearch-9k: A challenging benchmark dataset of deep-research agent. arXiv preprint arXiv:2603.01152. — [arXiv:2603.01152](https://arxiv.org/abs/2603.01152) find
  30. Guangzhi Xiong, Qiao Jin, Xiao Wang, Minjia Zhang, Zhiyong Lu, and Aidong Zhang. 2024. Improving retrieval-augmented generation in medicine with iterative follow-up questions. In Biocomputing 2025: Proceedings of the Pacific Symposium, pages 199– 214. World Scientific. find
  31. Derong Xu, Xinhang Li, Ziheng Zhang, Zhenxi Lin, Zhihong Zhu, Zhi Zheng, Xian Wu, Xiangyu Zhao, Tong Xu, and Enhong Chen. 2025. Harnessing large language models for knowledge graph question answering via adaptive multi-aspect retrieval-augmentation. In Proceedings of the AAAI Conference on Artificia… find
  32. Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2024. Recomp: Improving retrieval-augmented lms with context compression and selective augmentation. In The Twelfth International Conference on Learning Representations. find
  33. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600.
  34. Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, and Liang He. 2025. Optimizing question semantic space for dynamic retrieval-augmented multi-hop question answering. arXiv preprint arXiv:2506.00491. find
  35. Wenlin Zhang, Kuicai Dong, Junyi Li, Yingyi Zhang, Xiaopeng Li, Pengyue Jia, Yi Wen, Derong Xu, Maolin Wang, Yichao Wang, and 1 others. 2026. To search or not to search: Aligning the decision boundary of deep search agents via causal intervention. arXiv preprint arXiv:2602.03304. — [arXiv:2602.03304](https://arxiv.org/abs/2602.03304) find
  36. Wenlin Zhang, Xiaopeng Li, Yingyi Zhang, Pengyue Jia, Yichao Wang, Huifeng Guo, Yong Liu, and Xiangyu Zhao. 2025a. Deep research: A survey of autonomous research agents. arXiv preprint arXiv:2508.12752. — [arXiv:2508.12752](https://arxiv.org/abs/2508.12752) find
  37. Zijian Zhang, Shuchang Liu, Ziru Liu, Rui Zhong, Qingpeng Cai, Xiangyu Zhao, Chunxu Zhang, Qidong Liu, and Peng Jiang. 2025b. Llm-powered user simulator for recommender system. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 13339–13347. find
  38. Xiangyu Zhao, Long Xia, Jiliang Tang, and Dawei Yin. 2019. " deep reinforcement learning for search, recommendation, and online advertising: a survey" by xiangyu zhao, long xia, jiliang tang, and dawei yin with martin vesely as coordinator. ACM sigweb newsletter, 2019(Spring):1–15. find
  39. Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, and Wei Hu. 2025. Mitigating lost-in-retrieval problems in retrieval augmented multi-hop question answering. arXiv preprint arXiv:2502.14245.
  40. Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Qi Zhang. 2024. Efficientrag: Efficient retriever for multi-hop question answering. arXiv preprint arXiv:2408.04259. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yuqing-2026-search-r-structured-entity-aware/