--- title: "Eval-RAR — paper by Yu et al. (2026) — summary and ideas" description: "The authors argue that this causes aimless, repetitive searching, because the model never checks whether its evidence… 44 references." authors: ["Heng Yu", "Rui Li", "Qi Liu", "Wenjun Feng", "Junfeng Kang", "Yi Zhan"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.189/" doi: "10.18653/v1/2026.findings-acl.189" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yu-2026-eval-rar-evaluation-driven-retrieval/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2026-eval-rar-evaluation-driven-retrieval/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) / Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning # Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning **Authors:** Heng Yu, [Rui Li](https://md.research.elamur.ai/free/en/authors/rui-li/), [Qi Liu](https://md.research.elamur.ai/free/en/authors/qi-liu/), Wenjun Feng, Junfeng Kang and [Yi Zhan](https://md.research.elamur.ai/free/en/authors/yi-zhan/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.189/) · [PDF](https://aclanthology.org/2026.findings-acl.189.pdf) · [DOI 10.18653/v1/2026.findings-acl.189](https://doi.org/10.18653/v1/2026.findings-acl.189) · [OpenAlex](https://openalex.org/W7166899400) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary RL-trained retrieval-augmented reasoning systems usually alternate between thinking and searching. They absorb whatever documents come back and are rewarded only for the final answer. The authors argue that this causes aimless, repetitive searching, because the model never checks whether its evidence actually covers the question. Eval-RAR adds an explicit self-evaluation stage after every retrieval. In this stage, the model writes a rationale that either points to the supporting evidence or names the missing information, which then guides the next query. Training uses GRPO with a search engine in the loop. It combines an outcome reward with a fine-grained evaluation reward that gives intermediate feedback, mainly when the final answer is wrong, without needing golden reasoning trajectories. Across seven single-hop and multi-hop QA benchmarks, using Qwen2.5-3B Base and Instruct models, Eval-RAR beats prior approaches such as Search-R1. The work shows that process-level feedback on evidence sufficiency helps small models learn real multi-step search strategies. ## Key points - The core idea is a "Search-then-Evaluate" loop with tagged steps (think, search, information, evaluate, answer), optimized via GRPO with KL regularization against a frozen reference model. - Ablation: removing the evaluation reward lowers average EM from 0.413 to 0.360 (Base) and from 0.404 to 0.353 (Instruct). The largest drops occur on multi-hop sets such as Bamboogle and Musique. - Training dynamics follow a U-shape. Response length first falls from about 1400 to about 650 tokens as redundancy is pruned, then grows again after roughly step 125. Valid searches per trajectory rise from about 1.1 to over 2.2. - Search-R1-Base stays at about 1.0 search per trajectory, while Eval-RAR-Base exceeds 2.25. Training is smoother for Base than for Instruct models. - Limitations: only 3B models were tested, and the extra evaluation step adds inference cost. *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 Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works 🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works ## Cite Cite as: Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang and Yi Zhan. 2026. Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yu2026eval, title = {{Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning}}, author = {Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang and Yi Zhan}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.189}, url = {https://doi.org/10.18653/v1/2026.findings-acl.189} } ``` - [← previous EvaHan 2026 Ancient Books Multimodal OCR and Layout Analysis System Technical Report](https://md.research.elamur.ai/free/en/papers/zheng-2026-evahan-2026-ancient-books-multimodal/) - [next → Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring](https://md.research.elamur.ai/free/en/papers/kubesch-2026-evaluating-austrian-level-german-essays/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) ## References 44 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. 2. Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen. 2025. [Research: Learning to reason with search for llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/chen-2025-research-learning-reason-search-llms/). Preprint, arXiv:2503.19470. 3. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, and 16 others. 2024.… [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Yunxuan+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+Albert+Webson%2C+Shixiang+Shane+Gu%2C+Zhuyun+Dai%2C+Mirac+Suzgun%2C+X) 4. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in ll…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/) 5. DeepSeek-AI, Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y. Wu, Yukun Li, Huazuo Gao, Shirong Ma, Wangding Zeng, Xiao Bi, Zihui Gu, Hanwei Xu, Damai Dai, Kai Dong, Liyue Zhang, Yishi Piao, and 21 others. 2024. [Deepseek-coder-v2: Breaking the barrier of closed-source models…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2024-deepseek-coder-v2-breaking-barrier/) 6. Weibo Gao, Qi Liu, Linan Yue, Fangzhou Yao, Rui Lv, Zheng Zhang, Hao Wang, and Zhenya Huang. 2025. Agent4edu: Generating learner response data by generative agents for intelligent education systems. In Thirty-Ninth AAAI Conference on Artificial Intelligence, Thirty-Seventh Conference on Innovative A… [find](https://scholar.google.com/scholar?q=Weibo+Gao%2C+Qi+Liu%2C+Linan+Yue%2C+Fangzhou+Yao%2C+Rui+Lv%2C+Zheng+Zhang%2C+Hao+Wang%2C+and+Zhenya+Huang%2E+2025%2E+Agent4edu%3A+Generating+learner+response+data+by+generative+agents+for+intelligent+education+systems%2E+I) 7. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997. 8. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. [Retrieval augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research,… 9. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Comm… 10. 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](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). Preprint, arXiv:2503.09516. 11. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. [TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver… 12. 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](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli… 13. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/) 14. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP 2023, Koblenz… 15. 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](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Proc… 16. Rui Li, Liyang He, Qi Liu, Zheng Zhang, Heng Yu, Yuyang Ye, Linbo Zhu, and Yu Su. 2025a. Uni-RAG: Unified query understanding method for retrieval augmented generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14163–141… [find](https://scholar.google.com/scholar?q=Rui+Li%2C+Liyang+He%2C+Qi+Liu%2C+Zheng+Zhang%2C+Heng+Yu%2C+Yuyang+Ye%2C+Linbo+Zhu%2C+and+Yu+Su%2E+2025a%2E+Uni%2DRAG%3A+Unified+query+understanding+method+for+retrieval+augmented+generation%2E+In+Proceedings+of+the+63rd+Annu) 17. Jinchang Luo, Mingquan Cheng, Fan Wan, Ni Li, Xiaoling Xia, Shuangshuang Tian, Tingcheng Bian, Haiwei Wang, Haohuan Fu, and Yan Tao. 2025. Globalrag: Enhancing global reasoning in multi-hop question answering via reinforcement learning. Preprint, arXiv:2510.20548. — [arXiv:2510.20548](https://arxiv.org/abs/2510.20548) [find](https://scholar.google.com/scholar?q=Jinchang+Luo%2C+Mingquan+Cheng%2C+Fan+Wan%2C+Ni+Li%2C+Xiaoling+Xia%2C+Shuangshuang+Tian%2C+Tingcheng+Bian%2C+Haiwei+Wang%2C+Haohuan+Fu%2C+and+Yan+Tao%2E+2025%2E+Globalrag%3A+Enhancing+global+reasoning+in+multi%2Dhop+question+a) 18. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem) 19. OpenAI, :, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, and 244 others. 2024. [Openai o1 sy…](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/) 20. Long Ouyang, Jeffrey 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 F. Christiano, Jan Leike, and Ryan Lowe. 2022.… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/) 21. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5687–5711, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computation) 22. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025b. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5420–5438, Suzhou, China. Asso… 23. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+) 24. Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2024. [RA-DIT: retrieval-augmented dual instruction tuning](https://md.research.elamur.ai/free/en/papers/lin-2023-ra-dit-retrieval-augmented-dual/). In The Twelfth International Conference on Learning Representati… 25. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. Preprint, arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+Preprint%2C+arXiv%3A1707%2E06347%2E) 26. Qi Liu, Zhenya Huang, Yu Yin, Enhong Chen, Hui Xiong, Yu Su, and Guoping Hu. 2021. EKT: exercise-aware knowledge tracing for student performance prediction. IEEE Trans. Knowl. Data Eng., 33(1):100– 115. [find](https://scholar.google.com/scholar?q=Qi+Liu%2C+Zhenya+Huang%2C+Yu+Yin%2C+Enhong+Chen%2C+Hui+Xiong%2C+Yu+Su%2C+and+Guoping+Hu%2E+2021%2E+EKT%3A+exercise%2Daware+knowledge+tracing+for+student+performance+prediction%2E+IEEE+Trans%2E+Knowl%2E+Data+Eng%2E%2C+33%281%29%3A100%E2%80%93+11) 27. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). Preprint, arXiv:2402.03300. 28. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. [Hybridflow: A flexible and efficient RLHF framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, EuroSys 2025, Rotterdam, The Netherlands, 30 March 20… 29. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Richard James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2024. [REPLUG: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hum… 30. Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, and Xiang Wang. 2025. [Search and refine during think: Facilitating knowledge refinement for improved retrieval-augmented reasoning](https://md.research.elamur.ai/free/en/papers/shi-2025-search-refine-during-think-facilitating/). Preprint, arXiv:2505.11277. 31. Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. [R1-searcher: Incentivizing the search capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/song-2025-r1-searcher-incentivizing-search/). Preprint, arXiv:2503.05592. 32. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. MuSiQue: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+MuSiQue%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Transactions+of+the+Association+for+Computational+Li) 33. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p… 34. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). Preprint, arXiv:2212.03533. 35. 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](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi… 36. Wenda Wei, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Lixin Su, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, and Xueqi Cheng. 2025. Thinking forward and backward: Multi-objective reinforcement learning for retrieval-augmented reasoning. Preprint, arXiv:2511.09109. — [arXiv:2511.09109](https://arxiv.org/abs/2511.09109) [find](https://scholar.google.com/scholar?q=Wenda+Wei%2C+Yu%2DAn+Liu%2C+Ruqing+Zhang%2C+Jiafeng+Guo%2C+Lixin+Su%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Maarten+de+Rijke%2C+and+Xueqi+Cheng%2E+2025%2E+Thinking+forward+and+backward%3A+Multi%2Dobjective+reinforcement+learning+fo) 37. Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, and Jie Zhou. 2024. Unsupervised information refinement training of large language models for retrieval-augmented generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:… [find](https://scholar.google.com/scholar?q=Shicheng+Xu%2C+Liang+Pang%2C+Mo+Yu%2C+Fandong+Meng%2C+Huawei+Shen%2C+Xueqi+Cheng%2C+and+Jie+Zhou%2E+2024%2E+Unsupervised+information+refinement+training+of+large+language+models+for+retrieval%2Daugmented+generation%2E+In) 38. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. [HotpotQA: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369… 39. Heng Yu, Junfeng Kang, Rui Li, Qi Liu, Liyang He, Zhenya Huang, Shuanghong Shen, and Junyu Lu. 2025. CA-GAR: Context-aware alignment of LLM generation for document retrieval. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5836–5849, Vienna, Austria. Association for Com… [find](https://scholar.google.com/scholar?q=Heng+Yu%2C+Junfeng+Kang%2C+Rui+Li%2C+Qi+Liu%2C+Liyang+He%2C+Zhenya+Huang%2C+Shuanghong+Shen%2C+and+Junyu+Lu%2E+2025%2E+CA%2DGAR%3A+Context%2Daware+alignment+of+LLM+generation+for+document+retrieval%2E+In+Findings+of+the+Associ) 40. Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, and Junbo Zhao. 2025a. LeTS: Learning to think-and-search via process-and-outcome reward hybridization. In Proceedings of the 2025 Conference on Empirical Methods in Natural Lang… [find](https://scholar.google.com/scholar?q=Qi+Zhang%2C+Shouqing+Yang%2C+Lirong+Gao%2C+Hao+Chen%2C+Xiaomeng+Hu%2C+Jinglei+Chen%2C+Jiexiang+Wang%2C+Sheng+Guo%2C+Bo+Zheng%2C+Haobo+Wang%2C+and+Junbo+Zhao%2E+2025a%2E+LeTS%3A+Learning+to+think%2Dand%2Dsearch+via+process%2Dand%2Doutc) 41. Zheng Zhang, Ning Li, Qi Liu, Rui Li, Weibo Gao, Qingyang Mao, Zhenya Huang, Baosheng Yu, and Dacheng Tao. 2025b. The other side of the coin: Exploring fairness in retrieval-augmented generation. Preprint, arXiv:2504.12323. — [arXiv:2504.12323](https://arxiv.org/abs/2504.12323) [find](https://scholar.google.com/scholar?q=Zheng+Zhang%2C+Ning+Li%2C+Qi+Liu%2C+Rui+Li%2C+Weibo+Gao%2C+Qingyang+Mao%2C+Zhenya+Huang%2C+Baosheng+Yu%2C+and+Dacheng+Tao%2E+2025b%2E+The+other+side+of+the+coin%3A+Exploring+fairness+in+retrieval%2Daugmented+generation%2E+Prep) 42. Xuhui Zheng, Kang An, Ziliang Wang, Yuhang Wang, and Yichao Wu. 2025a. [StepSearch: Igniting LLMs search ability via step-wise proximal policy optimization](https://md.research.elamur.ai/free/en/papers/zheng-2025-stepsearch-igniting-llms-search-ability/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21816–21841, Suzhou, China. Association for Com… 43. Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. 2025b. [Deepresearcher: Scaling deep research via reinforcement learning in real-world environments](https://md.research.elamur.ai/free/en/papers/zheng-2025-deepresearcher-scaling-deep-research-reinforcement/). Preprint, arXiv:2504.03160. 44. Yan Zhuang, Qi Liu, Zhenya Huang, Zhi Li, Binbin Jin, Haoyang Bi, Enhong Chen, and Shijin Wang. 2022. A robust computerized adaptive testing approach in educational question retrieval. In SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Mad… [find](https://scholar.google.com/scholar?q=Yan+Zhuang%2C+Qi+Liu%2C+Zhenya+Huang%2C+Zhi+Li%2C+Binbin+Jin%2C+Haoyang+Bi%2C+Enhong+Chen%2C+and+Shijin+Wang%2E+2022%2E+A+robust+computerized+adaptive+testing+approach+in+educational+question+retrieval%2E+In+SIGIR+%E2%80%9922%3A+T) *Updated 2 November 2026*