{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:06:35Z","timestamp":1784138795832,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"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":"Strategic Priority Research Program of the CAS","award":["XDB0680102"],"award-info":[{"award-number":["XDB0680102"]}]},{"name":"National Natural Science Foundation of China","award":["62472408"],"award-info":[{"award-number":["62472408"]}]},{"name":"National Natural Science Foundation of China","award":["U25B2076"],"award-info":[{"award-number":["U25B2076"]}]},{"name":"National Natural Science Foundation of China","award":["62441229"],"award-info":[{"award-number":["62441229"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1011602"],"award-info":[{"award-number":["2023YFA1011602"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809941","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3970-3975","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Is a Busy Search Agent a Good One? Overthinking and Overretrieval at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8548-0936","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-2541","authenticated-orcid":false,"given":"Ruqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9125-5097","authenticated-orcid":false,"given":"Yu-An","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1246-1740","authenticated-orcid":false,"given":"Lixin","family":"Su","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Beijing, China, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and University of Chinese Academy of Sciences, Beijing, 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":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. arXiv preprint arXiv:2310.11511","author":"Asai Akari","year":"2023","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. arXiv preprint arXiv:2310.11511 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Luca Soldaini, Noah A Smith, Dirk Groeneveld, Pang Wei Koh, et al.","author":"Bhagia Akshita","year":"2024","unstructured":"Akshita Bhagia, Jiacheng Liu, Alexander Wettig, David Heineman, Oyvind Tafjord, Ananya Harsh Jha, Luca Soldaini, Noah A Smith, Dirk Groeneveld, Pang Wei Koh, et al., 2024. Establishing task scaling laws via compute-efficient model ladders. arXiv preprint arXiv:2412.04403 (2024)."},{"key":"e_1_3_2_1_4_1","unstructured":"Xingyu Chen Jiahao Xu Tian Liang Zhiwei He Jianhui Pang Dian Yu Linfeng Song Qiuzhi Liu Mengfei Zhou Zhuosheng Zhang et al. 2024. Do not think that much for 2 3=? on the overthinking of o1-like llms. arXiv preprint arXiv:2412.21187 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Length-controlled alpacaeval: A simple way to debias automatic evaluators. arXiv preprint arXiv:2404.04475","author":"Dubois Yann","year":"2024","unstructured":"Yann Dubois, Bal\u00e1zs Galambosi, Percy Liang, and Tatsunori B Hashimoto. 2024. Length-controlled alpacaeval: A simple way to debias automatic evaluators. arXiv preprint arXiv:2404.04475 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill? arXiv preprint arXiv:2504.06514","author":"Fan Chenrui","year":"2025","unstructured":"Chenrui Fan, Ming Li, Lichao Sun, and Tianyi Zhou. 2025. Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill? arXiv preprint arXiv:2504.06514 (2025)."},{"key":"e_1_3_2_1_7_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024. A survey on llm-as-a-judge. The Innovation (2024)."},{"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. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1274"},{"key":"e_1_3_2_1_10_1","volume-title":"Training large language models to reason in a continuous latent space. arXiv preprint arXiv:2412.06769","author":"Hao Shibo","year":"2024","unstructured":"Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. 2024. Training large language models to reason in a continuous latent space. arXiv preprint arXiv:2412.06769 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"LLM-as-a-Judge: Reassessing the Performance of LLMs in Extractive QA. arXiv preprint arXiv:2504.11972","author":"Ho Xanh","year":"2025","unstructured":"Xanh Ho, Jiahao Huang, Florian Boudin, and Akiko Aizawa. 2025. LLM-as-a-Judge: Reassessing the Performance of LLMs in Extractive QA. arXiv preprint arXiv:2504.11972 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Zijuan Lin, et al.","author":"Hong Sirui","year":"2023","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al., 2023. MetaGPT: Meta programming for a multi-agent collaborative framework. In The twelfth international conference on learning representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516","author":"Jin Bowen","year":"2025","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 preprint arXiv:2503.09516 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Rearag: Knowledge-guided reasoning enhances factuality of large reasoning models with iterative retrieval augmented generation. arXiv preprint arXiv:2503.21729","author":"Lee Zhicheng","year":"2025","unstructured":"Zhicheng Lee, Shulin Cao, Jinxin Liu, Jiajie Zhang, Weichuan Liu, Xiaoyin Che, Lei Hou, and Juanzi Li. 2025. Rearag: Knowledge-guided reasoning enhances factuality of large reasoning models with iterative retrieval augmented generation. arXiv preprint arXiv:2503.21729 (2025)."},{"key":"e_1_3_2_1_16_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_17_1","volume-title":"From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline. arXiv preprint arXiv:2406.11939","author":"Li Tianle","year":"2024","unstructured":"Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E Gonzalez, and Ion Stoica. 2024. From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline. arXiv preprint arXiv:2406.11939 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Torl: Scaling tool-integrated rl. arXiv preprint arXiv:2503.23383","author":"Li Xuefeng","year":"2025","unstructured":"Xuefeng Li, Haoyang Zou, and Pengfei Liu. 2025. Torl: Scaling tool-integrated rl. arXiv preprint arXiv:2503.23383 (2025)."},{"key":"e_1_3_2_1_19_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Lin Bill Yuchen","year":"2024","unstructured":"Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu, Faeze Brahman, Abhilasha Ravichander, Valentina Pyatkin, Nouha Dziri, Ronan Le Bras, and Yejin Choi. 2024. Wildbench: Benchmarking llms with challenging tasks from real users in the wild. arXiv preprint arXiv:2406.04770 (2024)."},{"key":"e_1_3_2_1_20_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.624"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2023.04.023"},{"key":"e_1_3_2_1_23_1","volume-title":"First Conference on Language Modeling.","author":"Rein David","year":"2024","unstructured":"David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. Gpqa: A graduate-level google-proof q&a benchmark. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn.2016.164"},{"key":"e_1_3_2_1_26_1","volume-title":"Evaluation metrics in the era of GPT-4: Reliably evaluating large language models on sequence to sequence tasks. arXiv preprint arXiv:2310.13800","author":"Sottana Andrea","year":"2023","unstructured":"Andrea Sottana, Bin Liang, Kai Zou, and Zheng Yuan. 2023. Evaluation metrics in the era of GPT-4: Reliably evaluating large language models on sequence to sequence tasks. arXiv preprint arXiv:2310.13800 (2023)."},{"key":"e_1_3_2_1_27_1","unstructured":"Yang Sui Yu-Neng Chuang Guanchu Wang Jiamu Zhang Tianyi Zhang Jiayi Yuan Hongyi Liu Andrew Wen Shaochen Zhong Na Zou et al. 2025. Stop overthinking: A survey on efficient reasoning for large language models. arXiv preprint arXiv:2503.16419 (2025)."},{"key":"e_1_3_2_1_28_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Qwq: Reflect deeply on the boundaries of the unknown. Hugging Face","author":"Team Qwen","year":"2024","unstructured":"Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. Hugging Face (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Codeif-bench: Evaluating instruction-following capabilities of large language models in interactive code generation. arXiv preprint arXiv:2503.22688","author":"Wang Peiding","year":"2025","unstructured":"Peiding Wang, Li Zhang, Fang Liu, Lin Shi, Minxiao Li, Bo Shen, and An Fu. 2025b. Codeif-bench: Evaluating instruction-following capabilities of large language models in interactive code generation. arXiv preprint arXiv:2503.22688 (2025)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.30"},{"key":"e_1_3_2_1_33_1","volume-title":"Meta-cognition and worry: A cognitive model of generalized anxiety disorder. Behavioural and cognitive psychotherapy","author":"Wells Adrian","year":"1995","unstructured":"Adrian Wells. 1995. Meta-cognition and worry: A cognitive model of generalized anxiety disorder. Behavioural and cognitive psychotherapy, Vol. 23, 3 (1995), 301-320."},{"key":"e_1_3_2_1_34_1","volume-title":"A survey of llm-based deep search agents: Paradigm, optimization, evaluation, and challenges. arXiv preprint arXiv:2508.05668","author":"Xi Yunjia","year":"2025","unstructured":"Yunjia Xi, Jianghao Lin, Yongzhao Xiao, Zheli Zhou, Rong Shan, Te Gao, Jiachen Zhu, Weiwen Liu, Yong Yu, and Weinan Zhang. 2025. A survey of llm-based deep search agents: Paradigm, optimization, evaluation, and challenges. arXiv preprint arXiv:2508.05668 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Over-Searching in Search-Augmented Large Language Models. arXiv preprint arXiv:2601.05503","author":"Xie Roy","year":"2026","unstructured":"Roy Xie, Deepak Gopinath, David Qiu, Dong Lin, Haitian Sun, Saloni Potdar, and Bhuwan Dhingra. 2026. Over-Searching in Search-Augmented Large Language Models. arXiv preprint arXiv:2601.05503 (2026)."},{"key":"e_1_3_2_1_36_1","volume-title":"A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications. arXiv preprint arXiv:2506.12594","author":"Xu Renjun","year":"2025","unstructured":"Renjun Xu and Jingwen Peng. 2025. A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications. arXiv preprint arXiv:2506.12594 (2025)."},{"key":"e_1_3_2_1_37_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_38_1","volume-title":"Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents. arXiv preprint arXiv:2505.12065","author":"Yang Tiannuo","year":"2025","unstructured":"Tiannuo Yang, Zebin Yao, Bowen Jin, Lixiao Cui, Yusen Li, Gang Wang, and Xiaoguang Liu. 2025. Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents. arXiv preprint arXiv:2505.12065 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"Improve llm-as-a-judge ability as a general ability. arXiv preprint arXiv:2502.11689","author":"Yu Jiachen","year":"2025","unstructured":"Jiachen Yu, Shaoning Sun, Xiaohui Hu, Jiaxu Yan, Kaidong Yu, and Xuelong Li. 2025. Improve llm-as-a-judge ability as a general ability. arXiv preprint arXiv:2502.11689 (2025)."}],"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":"2026-07-15T17:16:50Z","timestamp":1784135810000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809941"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":39,"alternative-id":["10.1145\/3805712.3809941","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809941","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"}}]}}