{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:28Z","timestamp":1784179108959,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809961","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"4419-4425","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-0955","authenticated-orcid":false,"given":"Shengyao","family":"Zhuang","sequence":"first","affiliation":[{"name":"The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-4910","authenticated-orcid":false,"given":"Xueguang","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9007-3976","authenticated-orcid":false,"given":"Zheng","family":"Yao","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-5250","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-3391","authenticated-orcid":false,"given":"Bevan","family":"Koopman","sequence":"additional","affiliation":[{"name":"CSIRO, St Lucia, QLD, Australia and The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7189","authenticated-orcid":false,"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[{"name":"The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Haodong Chen Shengyao Zhuang Zheng Yao Guido Zuccon and Teerapong Leelanupab. 2026. Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking. arXiv:2602.22591 [cs.IR] doi:10.1145\/3805712.3808558","DOI":"10.1145\/3805712.3808558"},{"key":"e_1_3_2_1_2_1","volume-title":"Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=yzloNYH3QN","author":"Chen Shijie","year":"2025","unstructured":"Shijie Chen, Bernal Jimenez Gutierrez, and Yu Su. 2025a. Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=yzloNYH3QN"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714863"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730287"},{"key":"e_1_3_2_1_5_1","volume-title":"Overview of the TREC 2020 deep learning track. arXiv:2102","author":"Craswell Nick","year":"2021","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. arXiv:2102.07662 [cs.IR] https:\/\/arxiv.org\/abs\/2102.07662"},{"key":"e_1_3_2_1_6_1","volume-title":"Overview of the TREC 2019 deep learning track. arXiv:2003","author":"Craswell Nick","year":"2003","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv:2003.07820 [cs.IR] https:\/\/arxiv.org\/abs\/2003.07820"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591805"},{"key":"e_1_3_2_1_8_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025b. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 (2025). https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701551.3703583"},{"key":"e_1_3_2_1_10_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_11_1","unstructured":"Yuxuan Huang Yihang Chen Haozheng Zhang Kang Li Huichi Zhou Meng Fang Linyi Yang Xiaoguang Li Lifeng Shang Songcen Xu Jianye Hao Kun Shao and Jun Wang. 2025. Deep Research Agents: A Systematic Examination And Roadmap. arXiv:2506.18096 [cs.AI] https:\/\/arxiv.org\/abs\/2506.18096"},{"key":"e_1_3_2_1_12_1","unstructured":"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. arXiv:2503.09516 [cs.CL] https:\/\/arxiv.org\/abs\/2503.09516"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730338"},{"key":"e_1_3_2_1_14_1","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv:2211.09110 (2022). https:\/\/arxiv.org\/abs\/2211.09110"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_16_1","unstructured":"Wenhan Liu Xinyu Ma Weiwei Sun Yutao Zhu Yuchen Li Dawei Yin and Zhicheng Dou. 2026. ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability. arXiv:2508.07050 [cs.IR] https:\/\/arxiv.org\/abs\/2508.07050"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_18_1","unstructured":"Xueguang Ma Xinyu Zhang Ronak Pradeep and Jimmy Lin. 2023. Zero-Shot Listwise Document Reranking with a Large Language Model. arXiv:2305.02156 [cs.IR] https:\/\/arxiv.org\/abs\/2305.02156"},{"key":"e_1_3_2_1_19_1","unstructured":"Tong Niu Shafiq Joty Ye Liu Caiming Xiong Yingbo Zhou and Semih Yavuz. 2024. JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking. arXiv:2411.00142 [cs.CL] https:\/\/arxiv.org\/abs\/2411.00142"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Rodrigo Nogueira Zhiying Jiang and Jimmy Lin. 2020. Document Ranking with a Pretrained Sequence-to-Sequence Model. arXiv:2003.06713 [cs.IR] https:\/\/arxiv.org\/abs\/2003.06713","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_21_1","unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730323"},{"key":"e_1_3_2_1_23_1","unstructured":"Ronak Pradeep Sahel Sharifymoghaddam and Jimmy Lin. 2023a. RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models. arXiv:2309.15088 [cs.IR] https:\/\/arxiv.org\/abs\/2309.15088"},{"key":"e_1_3_2_1_24_1","unstructured":"Ronak Pradeep Sahel Sharifymoghaddam and Jimmy Lin. 2023b. RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! arXiv:2312.02724 [cs.IR] https:\/\/arxiv.org\/abs\/2312.02724"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_26_1","unstructured":"Qwen et al. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.249"},{"key":"e_1_3_2_1_28_1","volume-title":"ReasonIR: Training Retrievers for Reasoning Tasks. In Second Conference on Language Modeling. https:\/\/openreview.net\/forum?id=kkBCNLMbGj","author":"Shao Rulin","year":"2025","unstructured":"Rulin Shao, Rui Qiao, Varsha Kishore, Niklas Muennighoff, Xi Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen tau Yih, Pang Wei Koh, and Luke Zettlemoyer. 2025. ReasonIR: Training Retrievers for Reasoning Tasks. In Second Conference on Language Modeling. https:\/\/openreview.net\/forum?id=kkBCNLMbGj"},{"key":"e_1_3_2_1_29_1","unstructured":"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. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_1_30_1","volume-title":"Lei Fang, and Ji-Rong Wen.","author":"Song Huatong","year":"2025","unstructured":"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. arXiv:2503.05592 [cs.AI] https:\/\/arxiv.org\/abs\/2503.05592"},{"key":"e_1_3_2_1_31_1","volume-title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ykuc5q381b","author":"Su Hongjin","year":"2025","unstructured":"Hongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han yu Wang, Liu Haisu, Quan Shi, Zachary S Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O Arik, Danqi Chen, and Tao Yu. 2025. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ykuc5q381b"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88711-6_12"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_34_1","volume-title":"Zephyr: Direct Distillation of LM Alignment. arXiv:2310.16944 [cs.LG] https:\/\/arxiv.org\/abs\/2310.16944","author":"Tunstall Lewis","year":"2023","unstructured":"Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Kashif Rasul, Younes Belkada, Shengyi Huang, Leandro von Werra, Cl\u00e9mentine Fourrier, Nathan Habib, Nathan Sarrazin, Omar Sanseviero, Alexander M. Rush, and Thomas Wolf. 2023. Zephyr: Direct Distillation of LM Alignment. arXiv:2310.16944 [cs.LG] https:\/\/arxiv.org\/abs\/2310.16944"},{"key":"e_1_3_2_1_35_1","volume-title":"TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl.","author":"von Werra Leandro","year":"2020","unstructured":"Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallou\u00e9dec. 2020. TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl."},{"key":"e_1_3_2_1_36_1","unstructured":"Orion Weller Kathryn Ricci Eugene Yang Andrew Yates Dawn Lawrie and Benjamin Van Durme. 2025. Rank1: Test-Time Compute for Reranking in Information Retrieval. arXiv:2502.18418 [cs.IR] https:\/\/arxiv.org\/abs\/2502.18418"},{"key":"e_1_3_2_1_37_1","unstructured":"Zhichao Xu. 2024. RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers. arXiv:2403.18276 [cs.IR] https:\/\/arxiv.org\/abs\/2403.18276"},{"key":"e_1_3_2_1_38_1","volume-title":"Benjamin Van Durme, and Dawn Lawrie","author":"Yang Eugene","year":"2025","unstructured":"Eugene Yang, Andrew Yates, Kathryn Ricci, Orion Weller, Vivek Chari, Benjamin Van Durme, and Dawn Lawrie. 2025. Rank-K: Test-Time Reasoning for Listwise Reranking. arXiv:2505.14432 [cs.IR] https:\/\/arxiv.org\/abs\/2505.14432"},{"key":"e_1_3_2_1_39_1","unstructured":"Weihao Zeng Yuzhen Huang Wei Liu Keqing He Qian Liu Zejun Ma and Junxian He. 2025. 7B Model and 8K Examples: Emerging Reasoning with Reinforcement Learning is Both Effective and Efficient. https:\/\/hkust-nlp.notion.site\/simplerl-reason. Notion Blog."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.22"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.31"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.590"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4106-4109","author":"Zuccon Guido","year":"2025","unstructured":"Guido Zuccon, Shengyao Zhuang, and Xueguang Ma. 2025. R2LLMs: Retrieval and Ranking with LLMs. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 4106-4109."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:24:22Z","timestamp":1784136262000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":44,"alternative-id":["10.1145\/3805712.3809961","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809961","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}