{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:46Z","timestamp":1784138686735,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":16,"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\/3805712.3809865","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"4409-4413","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GraphSynthQA: Knowledge-Graph-Guided Query Synthesis and Step-Level Preference Optimization for Web Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0336-6119","authenticated-orcid":false,"given":"Chiwei","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0881-3839","authenticated-orcid":false,"given":"Mingxuan","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0976-1634","authenticated-orcid":false,"given":"Benfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9947-039X","authenticated-orcid":false,"given":"Shengzhuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Yuanshi Technology Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7840-598X","authenticated-orcid":false,"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Yuanshi Technology Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Saku Sugawara, and Akiko Aizawa.","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. arXiv:2011.01060 [cs.CL] https:\/\/arxiv.org\/abs\/2011.01060"},{"key":"e_1_3_2_1_2_1","unstructured":"Kuan Li Zhongwang Zhang Huifeng Yin Liwen Zhang Litu Ou Jialong Wu Wenbiao Yin Baixuan Li Zhengwei Tao Xinyu Wang Weizhou Shen Junkai Zhang Dingchu Zhang Xixi Wu Yong Jiang Ming Yan Pengjun Xie Fei Huang and Jingren Zhou. 2025c. WebSailor: Navigating Super-human Reasoning for Web Agent. arXiv:2507.02592 [cs.CL] https:\/\/arxiv.org\/abs\/2507.02592"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4028"},{"key":"e_1_3_2_1_4_1","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:2501.05366 [cs.AI] https:\/\/arxiv.org\/abs\/2501.05366"},{"key":"e_1_3_2_1_5_1","unstructured":"Xiaoxi Li Jiajie Jin Guanting Dong Hongjin Qian Yongkang Wu Ji-Rong Wen Yutao Zhu and Zhicheng Dou. 2025b. WebThinker: Empowering Large Reasoning Models with Deep Research Capability. arXiv:2504.21776 [cs.CL] https:\/\/arxiv.org\/abs\/2504.21776"},{"key":"e_1_3_2_1_6_1","unstructured":"Junteng Liu Yunji Li Chi Zhang Jingyang Li Aili Chen Ke Ji Weiyu Cheng Zijia Wu Chengyu Du Qidi Xu Jiayuan Song Zhengmao Zhu Wenhu Chen Pengyu Zhao and Junxian He. 2025. WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents. arXiv:2509.06501 [cs.CL] https:\/\/arxiv.org\/abs\/2509.06501"},{"key":"e_1_3_2_1_7_1","unstructured":"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 Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tianyi Tang Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Stefano Ermon Christopher D. Manning and Chelsea Finn. 2024. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arXiv:2305.18290 [cs.LG] https:\/\/arxiv.org\/abs\/2305.18290","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_1_9_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_1_10_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_11_1","unstructured":"Wenxuan Shi Haochen Tan Chuqiao Kuang Xiaoguang Li Xiaozhe Ren Chen Zhang Hanting Chen Yasheng Wang Lifeng Shang Fisher Yu and Yunhe Wang. 2025. Pangu DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning. arXiv:2505.24332 [cs.CL] https:\/\/arxiv.org\/abs\/2505.24332"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"crossref","unstructured":"Harsh Trivedi Niranjan Balasubramanian Tushar Khot and Ashish Sabharwal. 2022. MuSiQue: Multihop Questions via Single-hop Question Composition. arXiv:2108.00573 [cs.CL] https:\/\/arxiv.org\/abs\/2108.00573","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_2_1_14_1","unstructured":"Jialong Wu Baixuan Li Runnan Fang Wenbiao Yin Liwen Zhang Zhengwei Tao Dingchu Zhang Zekun Xi Gang Fu Yong Jiang Pengjun Xie Fei Huang and Jingren Zhou. 2025. WebDancer: Towards Autonomous Information Seeking Agency. arXiv:2505.22648 [cs.CL] https:\/\/arxiv.org\/abs\/2505.22648"},{"key":"e_1_3_2_1_15_1","unstructured":"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:2210.03629 [cs.CL] https:\/\/arxiv.org\/abs\/2210.03629"},{"key":"e_1_3_2_1_16_1","unstructured":"Yuhang Zhou Kai Zheng Qiguang Chen Mengkang Hu Qingfeng Sun Can Xu and Jingjing Chen. 2026. OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents. arXiv:2601.18467 [cs.AI] https:\/\/arxiv.org\/abs\/2601.18467"}],"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":"2026-07-15T17:14:58Z","timestamp":1784135698000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":16,"alternative-id":["10.1145\/3805712.3809865","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809865","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"}}]}}