{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:10:17Z","timestamp":1784139017867,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":71,"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"}],"funder":[{"name":"Engineering and Physical Sciences Research Council (EPSRC)","award":["EP\/V025708\/1"],"award-info":[{"award-number":["EP\/V025708\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808557","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3006-3016","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Text Ranking in Deep Research"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1434-7596","authenticated-orcid":false,"given":"Chuan","family":"Meng","sequence":"first","affiliation":[{"name":"The University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8380-1368","authenticated-orcid":false,"given":"Litu","family":"Ou","sequence":"additional","affiliation":[{"name":"The University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8914-2659","authenticated-orcid":false,"given":"Sean","family":"MacAvaney","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-8651","authenticated-orcid":false,"given":"Jeff","family":"Dalton","sequence":"additional","affiliation":[{"name":"The University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Sandhini Agarwal Lama Ahmad Jason Ai Sam Altman Andy Applebaum Edwin Arbus Rahul K Arora Yu Bai Bowen Baker Haiming Bao et al. 2025. gpt-oss-120b & gpt-oss-20b Model Card. arXiv preprint arXiv:2508.10925 (2025)."},{"key":"e_1_3_2_1_2_1","volume-title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation. arXiv preprint arXiv:2602.15547","author":"Akram Mohammad Kalim","year":"2026","unstructured":"Mohammad Kalim Akram, Saba Sturua, Nastia Havriushenko, Quentin Herreros, Michael G\u00fcnther, Maximilian Werk, and Han Xiao. 2026. jina-embeddings-v5-text: Task-Targeted Embedding Distillation. arXiv preprint arXiv:2602.15547 (2026)."},{"key":"e_1_3_2_1_3_1","unstructured":"Akari Asai Zeqiu Wu Yizhong Wang Avirup Sil and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve Generate and Critique through Self-Reflection. In ICLR."},{"key":"e_1_3_2_1_4_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv preprint arXiv:1611.09268","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv preprint arXiv:1611.09268 (2018)."},{"key":"e_1_3_2_1_5_1","first-page":"6334","article-title":"PyLate","author":"Chaffin Antoine","year":"2025","unstructured":"Antoine Chaffin and Rapha\u00ebl Sourty. 2025. PyLate: Flexible Training and Retrieval for Late Interaction Models. In CIKM. 6334-6339.","journal-title":"Flexible Training and Retrieval for Late Interaction Models. In CIKM."},{"key":"e_1_3_2_1_6_1","unstructured":"Zijian Chen Xueguang Ma Shengyao Zhuang Ping Nie Kai Zou Andrew Liu Joshua Green Kshama Patel Ruoxi Meng Mingyi Su et al. 2025. BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent. arXiv preprint arXiv:2508.06600 (2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"Overview of the TREC 2019 Deep Learning Track. In REC 2019.","author":"Craswell Nick","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M. Voorhees. 2019. Overview of the TREC 2019 Deep Learning Track. In REC 2019."},{"key":"e_1_3_2_1_8_1","first-page":"985","article-title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","author":"Dai Zhuyun","year":"2019","unstructured":"Zhuyun Dai and Jamie Callan. 2019. Deeper Text Understanding for IR with Contextual Neural Language Modeling. In SIGIR. 985-988.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Jeffrey Dalton Chenyan Xiong and Jamie Callan. 2021. TREC CAsT 2021: The Conversational Assistance Track Overview. In TREC.","DOI":"10.6028\/NIST.SP.500-335.cast-overview"},{"key":"e_1_3_2_1_10_1","first-page":"4171","article-title":"BERT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171-4186.","journal-title":"Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_1_11_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. arXiv preprint arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. arXiv preprint arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_12_1","first-page":"2288","article-title":"SPLADE","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021b. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR. 2288-2292.","journal-title":"In SIGIR."},{"key":"e_1_3_2_1_13_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_14_1","first-page":"200","article-title":"Term Frequency Normalisation Tuning for BM25 and DFR Models","author":"He Ben","year":"2005","unstructured":"Ben He and Iadh Ounis. 2005. Term Frequency Normalisation Tuning for BM25 and DFR Models. In ECIR. 200-214.","journal-title":"ECIR."},{"key":"e_1_3_2_1_15_1","first-page":"6609","article-title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","author":"Ho Xanh","year":"2020","unstructured":"Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps. In COLING. 6609-6625.","journal-title":"COLING."},{"key":"e_1_3_2_1_16_1","unstructured":"Edward J Hu Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_2_1_17_1","volume-title":"SAGE: Benchmarking and Improving Retrieval for Deep Research Agents. arXiv preprint arXiv:2602.05975","author":"Hu Tiansheng","year":"2026","unstructured":"Tiansheng Hu, Yilun Zhao, Canyu Zhang, Arman Cohan, and Chen Zhao. 2026. SAGE: Benchmarking and Improving Retrieval for Deep Research Agents. arXiv preprint arXiv:2602.05975 (2026)."},{"key":"e_1_3_2_1_18_1","unstructured":"Bowen Jin Hansi Zeng Zhenrui Yue Jinsung Yoon Sercan O Arik Dong Wang Hamed Zamani and Jiawei Han. 2025. Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning. In COLM."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/258525.258561"},{"key":"e_1_3_2_1_20_1","first-page":"39","article-title":"Colbert: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia. 2020. Colbert: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. In SIGIR. 39-48.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_21_1","first-page":"453","volume":"7","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al., 2019. Natural Questions: A Benchmark for Question Answering Research. TACL, Vol. 7 (2019), 453-466.","journal-title":"Natural Questions: A Benchmark for Question Answering Research. TACL"},{"key":"e_1_3_2_1_22_1","volume-title":"SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789","author":"Lassance Carlos","year":"2024","unstructured":"Carlos Lassance, Herv\u00e9 D\u00e9jean, Thibault Formal, and St\u00e9phane Clinchant. 2024. SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789 (2024)."},{"key":"e_1_3_2_1_23_1","unstructured":"Kuan Li Zhongwang Zhang Huifeng Yin Liwen Zhang Litu Ou Jialong Wu Wenbiao Yin Baixuan Li Zhengwei Tao Xinyu Wang et al. 2025b. WebSailor: Navigating Super-human Reasoning for Web Agent. arXiv preprint arXiv:2507.02592 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models. arXiv preprint arXiv:2501.05366","author":"Li Xiaoxi","year":"2025","unstructured":"Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. Search-o1: Agentic Search-Enhanced Large Reasoning Models. arXiv preprint arXiv:2501.05366 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Towards General Text Embeddings with Multi-stage Contrastive Learning. ArXiv","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards General Text Embeddings with Multi-stage Contrastive Learning. ArXiv (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02181-7"},{"key":"e_1_3_2_1_27_1","unstructured":"Junteng Liu Yunji Li Chi Zhang Jingyang Li Aili Chen Ke Ji Weiyu Cheng Zijia Wu Chengyu Du Qidi Xu et al. 2025. WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents. arXiv preprint arXiv:2509.06501 (2025)."},{"key":"e_1_3_2_1_28_1","first-page":"2421","article-title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","author":"Ma Xueguang","year":"2024","unstructured":"Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, and Jimmy Lin. 2024. Fine-Tuning LLaMA for Multi-Stage Text Retrieval. In SIGIR. 2421-2425.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_29_1","first-page":"1807","article-title":"System Initiative Prediction for Multi-turn Conversational Information Seeking","author":"Meng Chuan","year":"2023","unstructured":"Chuan Meng, Mohammad Aliannejadi, and Maarten de Rijke. 2023. System Initiative Prediction for Multi-turn Conversational Information Seeking. In CIKM. 1807-1817.","journal-title":"CIKM."},{"key":"e_1_3_2_1_30_1","first-page":"141","article-title":"Ranked List Truncation for Large Language Model-based Re-Ranking","author":"Meng Chuan","year":"2024","unstructured":"Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, and Maarten de Rijke. 2024. Ranked List Truncation for Large Language Model-based Re-Ranking. In SIGIR. 141-151.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_31_1","volume-title":"2026 a. Re-Rankers as Relevance Judges. arXiv preprint arXiv:2601.04455","author":"Meng Chuan","year":"2026","unstructured":"Chuan Meng, Jiqun Liu, Mohammad Aliannejadi, Fengran Mo, Jeff Dalton, and Maarten de Rijke. 2026 a. Re-Rankers as Relevance Judges. arXiv preprint arXiv:2601.04455 (2026)."},{"key":"e_1_3_2_1_32_1","first-page":"11","article-title":"b. Conversational Search: Foundations, Large Language Models, and Agents","author":"Meng Chuan","year":"2026","unstructured":"Chuan Meng, Fengran Mo, Mohammad Aliannejadi, Jeff Dalton, and Jian-Yun Nie. 2026 b. Conversational Search: Foundations, Large Language Models, and Agents. In ECIR. 11-18.","journal-title":"ECIR."},{"key":"e_1_3_2_1_33_1","first-page":"64","article-title":"Bridging the Gap: From Ad-hoc to Proactive Search in Conversations","author":"Meng Chuan","year":"2025","unstructured":"Chuan Meng, Francesco Tonolini, Fengran Mo, Nikolaos Aletras, Emine Yilmaz, and Gabriella Kazai. 2025. Bridging the Gap: From Ad-hoc to Proactive Search in Conversations. In SIGIR. 64-74.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_34_1","first-page":"6936","author":"Mo Fengran","year":"2025","unstructured":"Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, et al., 2025. UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations. In ACL. 6936-6949.","journal-title":"In ACL."},{"key":"e_1_3_2_1_35_1","unstructured":"Fengran Mo Zhan Su Yuchen Hui Jinghan Zhang Jia Ao Sun Zheyuan Liu Chao Zhang Tetsuya Sakai and Jian-Yun Nie. [n.d.]. OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG. In WWW. 2252\u20132262."},{"key":"e_1_3_2_1_36_1","first-page":"341","article-title":"Semantically Proportioned nDCG for Explaining ColBERT's Learning Process","author":"Mueller Ariane","year":"2025","unstructured":"Ariane Mueller and Craig Macdonald. 2025. Semantically Proportioned nDCG for Explaining ColBERT's Learning Process. In ECIR. 341-356.","journal-title":"ECIR."},{"key":"e_1_3_2_1_37_1","volume-title":"Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. arXiv preprint arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_1_38_1","first-page":"708","article-title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","author":"Nogueira Rodrigo","year":"2020","unstructured":"Rodrigo Nogueira, Zhiying Jiang, Ronak Pradeep, and Jimmy Lin. 2020. Document Ranking with a Pretrained Sequence-to-Sequence Model. In EMNLP. 708-718.","journal-title":"EMNLP."},{"key":"e_1_3_2_1_39_1","volume-title":"BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents. arXiv preprint arXiv:2510.23458","author":"Ou Litu","year":"2025","unstructured":"Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Pengjun Xie, Jingren Zhou, and Yong Jiang. 2025. BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents. arXiv preprint arXiv:2510.23458 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Paul Owoicho Jeffrey Dalton Mohammad Aliannejadi Leif Azzopardi Johanne R. Trippas and Svitlana Vakulenko. 2022. TREC CAsT 2022: Going Beyond User Ask and System Retrieve with Initiative and Response Generation. In TREC.","DOI":"10.6028\/NIST.SP.500-338.cast-overview"},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Stephen E. Robertson Steve Walker Susan Jones Micheline Hancock-Beaulieu and Mike Gatford. 1994. Okapi at TREC-3. In TREC.","DOI":"10.6028\/NIST.SP.500-225.adhoc-city"},{"key":"e_1_3_2_1_43_1","first-page":"3715","article-title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","author":"Santhanam Keshav","year":"2022","unstructured":"Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In NAACL. 3715-3734.","journal-title":"NAACL."},{"key":"e_1_3_2_1_44_1","volume-title":"Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen-tau Yih, Pang Wei Koh, et al.","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, et al., 2025. ReasonIR: Training Retrievers for Reasoning Tasks. arXiv preprint arXiv:2504.20595 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents. arXiv preprint arXiv:2601.14224","author":"Sharifymoghaddam Sahel","year":"2026","unstructured":"Sahel Sharifymoghaddam and Jimmy Lin. 2026. Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents. arXiv preprint arXiv:2601.14224 (2026)."},{"key":"e_1_3_2_1_46_1","volume-title":"Deep Research: A Systematic Survey. arXiv preprint arXiv:2512.02038","author":"Shi Zhengliang","year":"2025","unstructured":"Zhengliang Shi, Yiqun Chen, Haitao Li, Weiwei Sun, Shiyu Ni, Yougang Lyu, Run-Ze Fan, Bowen Jin, Yixuan Weng, Minjun Zhu, et al., 2025. Deep Research: A Systematic Survey. arXiv preprint arXiv:2512.02038 (2025)."},{"key":"e_1_3_2_1_47_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 preprint arXiv:2503.05592 (2025)."},{"key":"e_1_3_2_1_48_1","volume-title":"Liu Haisu, Quan Shi, Zachary S Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O Arik, Danqi Chen, and Tao Yu.","author":"Howard Yen Hongjin SU","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 ICLR."},{"key":"e_1_3_2_1_49_1","first-page":"1240","article-title":"Parametric Retrieval Augmented Generation","author":"Su Weihang","year":"2025","unstructured":"Weihang Su, Yichen Tang, Qingyao Ai, Junxi Yan, Changyue Wang, Hongning Wang, Ziyi Ye, Yujia Zhou, and Yiqun Liu. 2025. Parametric Retrieval Augmented Generation. In SIGIR. 1240-1250.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_50_1","unstructured":"Tongyi DeepResearch Team Baixuan Li Bo Zhang Dingchu Zhang Fei Huang Guangyu Li Guoxin Chen Huifeng Yin Jialong Wu Jingren Zhou Kuan Li Liangcai Su Litu Ou Liwen Zhang Pengjun Xie Rui Ye Wenbiao Yin Xinmiao Yu Xinyu Wang Xixi Wu Xuanzhong Chen Yida Zhao Zhen Zhang Zhengwei Tao Zhongwang Zhang Zile Qiao Chenxi Wang Donglei Yu Gang Fu Haiyang Shen Jiayin Yang Jun Lin Junkai Zhang Kui Zeng Li Yang Hailong Yin Maojia Song Ming Yan Minpeng Liao Peng Xia Qian Xiao Rui Min Ruixue Ding Runnan Fang Shaowei Chen Shen Huang Shihang Wang Shihao Cai Weizhou Shen Xiaobin Wang Xin Guan Xinyu Geng Yingcheng Shi Yuning Wu Zhuo Chen Zijian Li and Yong Jiang. 2025. Tongyi DeepResearch Technical Report. arXiv preprint arXiv:2510.24701 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_52_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_2_1_54_1","volume-title":"DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation. arXiv preprint arXiv:2601.09688","author":"Wang Yibo","year":"2026","unstructured":"Yibo Wang, Lei Wang, Yue Deng, Keming Wu, Yao Xiao, Huanjin Yao, Liwei Kang, Hai Ye, Yongcheng Jing, and Lidong Bing. 2026. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation. arXiv preprint arXiv:2601.09688 (2026)."},{"key":"e_1_3_2_1_55_1","volume-title":"Alex Tachard Passos, William Fedus, and Amelia Glaese.","author":"Wei Jason","year":"2025","unstructured":"Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. 2025. BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents. arXiv preprint arXiv:2504.12516 (2025)."},{"key":"e_1_3_2_1_56_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_57_1","volume-title":"On the Theoretical Limitations of Embedding-Based Retrieval. arXiv preprint arXiv:2508.21038","author":"Weller Orion","year":"2025","unstructured":"Orion Weller, Michael Boratko, Iftekhar Naim, and Jinhyuk Lee. 2025a. On the Theoretical Limitations of Embedding-Based Retrieval. arXiv preprint arXiv:2508.21038 (2025)."},{"key":"e_1_3_2_1_58_1","unstructured":"Orion Weller Kathryn Ricci Eugene Yang Andrew Yates Dawn Lawrie and Benjamin Van Durme. 2025b. Rank1: Test-Time Compute for Reranking in Information Retrieval. In COLM."},{"key":"e_1_3_2_1_59_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N Bennett Junaid Ahmed and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR."},{"key":"e_1_3_2_1_60_1","volume-title":"SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback. arXiv preprint arXiv:2601.18202","author":"Xu Fangyuan","year":"2026","unstructured":"Fangyuan Xu, Rujun Han, Yanfei Chen, Zifeng Wang, I Hsu, Jun Yan, Vishy Tirumalashetty, Eunsol Choi, Tomas Pfister, Chen-Yu Lee, et al., 2026 a. SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback. arXiv preprint arXiv:2601.18202 (2026)."},{"key":"e_1_3_2_1_61_1","volume-title":"2026 b. Self-Manager: Parallel Agent Loop for Long-form Deep Research. arXiv preprint arXiv:2601.17879","author":"Xu Yilong","year":"2026","unstructured":"Yilong Xu, Zhi Zheng, Xiang Long, Yujun Cai, and Yiwei Wang. 2026 b. Self-Manager: Parallel Agent Loop for Long-form Deep Research. arXiv preprint arXiv:2601.17879 (2026)."},{"key":"e_1_3_2_1_62_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025a. Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_63_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_64_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. 2025b. Rank-K: Test-Time Reasoning for Listwise Reranking. arXiv preprint arXiv:2505.14432 (2025)."},{"key":"e_1_3_2_1_65_1","first-page":"2369","article-title":"HotpotQA: A Dataset for Diverse","author":"Yang Zhilin","year":"2018","unstructured":"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. In EMNLP. 2369-2380.","journal-title":"Explainable Multi-hop Question Answering. In EMNLP."},{"key":"e_1_3_2_1_66_1","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik R Narasimhan and Yuan Cao. 2022. ReAct: Synergizing Reasoning and Acting in Language Models. In ICLR."},{"key":"e_1_3_2_1_67_1","unstructured":"Aohan Zeng Xin Lv Qinkai Zheng Zhenyu Hou Bin Chen Chengxing Xie Cunxiang Wang Da Yin Hao Zeng Jiajie Zhang et al. 2025. GLM-4.5: Agentic Reasoning and Coding (ARC) Foundation Models. arXiv preprint arXiv:2508.06471 (2025)."},{"key":"e_1_3_2_1_68_1","first-page":"3895","article-title":"Entropy-based Exploration Conduction for Multi-step Reasoning","author":"Zhang Jinghan","year":"2025","unstructured":"Jinghan Zhang, Xiting Wang, Fengran Mo, Yeyang Zhou, Wanfu Gao, and Kunpeng Liu. 2025b. Entropy-based Exploration Conduction for Multi-step Reasoning. In ACL. 3895-3906.","journal-title":"ACL."},{"key":"e_1_3_2_1_69_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025a. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."},{"key":"e_1_3_2_1_70_1","unstructured":"Peilin Zhou Bruce Leon Xiang Ying Can Zhang Yifan Shao Qichen Ye Dading Chong Zhiling Jin Chenxuan Xie Meng Cao et al. 2025. BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese. arXiv preprint arXiv:2504.19314 (2025)."},{"key":"e_1_3_2_1_71_1","volume-title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation. arXiv preprint arXiv:2206.10128","author":"Zhuang Shengyao","year":"2022","unstructured":"Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei, Ming Gong, Guido Zuccon, and Daxin Jiang. 2022. Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation. arXiv preprint arXiv:2206.10128 (2022)."}],"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":"2026-07-15T17:30:12Z","timestamp":1784136612000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":71,"alternative-id":["10.1145\/3805712.3808557","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808557","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"}}]}}