{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:23Z","timestamp":1784138723924,"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":"Research Project of Quancheng Laboratory, China","award":["QCL20250105"],"award-info":[{"award-number":["QCL20250105"]}]},{"name":"Key R&D Program of Shandong Province","award":["SYS202201"],"award-info":[{"award-number":["SYS202201"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808611","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3559-3567","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TEC: A Collection of Human Trial-and-error Trajectories for Problem Solving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8865-9653","authenticated-orcid":false,"given":"Xinkai","family":"Zhang","sequence":"first","affiliation":[{"name":"College of AI, Tsinghua University, Quancheng Laboratory, Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-5245","authenticated-orcid":false,"given":"Jingtao","family":"Zhan","sequence":"additional","affiliation":[{"name":"Institute of Data and Information, Tsinghua Shenzhen International Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"Quancheng Laboratory, Department of Computer Science and Technology, Tsinghua University, 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","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462800"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914675"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.500-308.session-overview"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450127"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358158"},{"key":"e_1_3_2_1_6_1","unstructured":"Mingyue Cheng Jie Ouyang Shuo Yu Ruiran Yan Yucong Luo Zirui Liu Daoyu Wang Qi Liu and Enhong Chen. 2025. Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning. arXiv:2511.14460 [cs.CL] https:\/\/arxiv.org\/abs\/2511.14460"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"C. Darwin. 1859. On the Origin of Species by Means of Natural Selection Or The Preservation of Favoured Races in the Struggle for Life. J. Murray. 06017473 https:\/\/books.google.co.jp\/books?id=jTZbAAAAQAAJ","DOI":"10.5962\/bhl.title.68064"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"e_1_3_2_1_9_1","volume-title":"serdyukovpv, and Will Cukierski","author":"Eugene","year":"2013","unstructured":"Eugene, serdyukovpv, and Will Cukierski. 2013. Personalized Web Search Challenge. https:\/\/kaggle.com\/competitions\/yandex-personalized-web-search-challenge. Kaggle."},{"key":"e_1_3_2_1_10_1","volume-title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. arXiv:2305.11738 [cs.CL] https:\/\/arxiv.org\/abs\/2305.11738","author":"Gou Zhibin","year":"2024","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2024. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. arXiv:2305.11738 [cs.CL] https:\/\/arxiv.org\/abs\/2305.11738"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Ehsan Kamalloo Nouha Dziri Charles L. A. Clarke and Davood Rafiei. 2023. Evaluating Open-Domain Question Answering in the Era of Large Language Models. arXiv:2305.06984 [cs.CL] https:\/\/arxiv.org\/abs\/2305.06984","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"e_1_3_2_1_14_1","volume-title":"Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela.","author":"Lewis Patrick","year":"2021","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:2005.11401 [cs.CL] https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1104"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_59"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-021-02022-8"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-010416-044022"},{"key":"e_1_3_2_1_20_1","unstructured":"Gr\u00e9goire Mialon Cl\u00e9mentine Fourrier Craig Swift Thomas Wolf Yann LeCun and Thomas Scialom. 2023. GAIA: a benchmark for General AI Assistants. arXiv:2311.12983 [cs.CL] https:\/\/arxiv.org\/abs\/2311.12983"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2910896.2925447"},{"key":"e_1_3_2_1_22_1","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders Xu Jiang Karl Cobbe Tyna Eloundou Gretchen Krueger Kevin Button Matthew Knight Benjamin Chess and John Schulman. 2022. WebGPT: Browser-assisted question-answering with human feedback. arXiv:2112.09332 [cs.CL] https:\/\/arxiv.org\/abs\/2112.09332"},{"key":"e_1_3_2_1_23_1","unstructured":"A. Newell and H.A. Simon. 2019. Human Problem Solving. Echo Point Books and Media. https:\/\/books.google.co.jp\/books?id=Gf8EwgEACAAJ"},{"key":"e_1_3_2_1_24_1","unstructured":"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 Ally Bennett Ananya Kumar Andre Saraiva Andrea Vallone Andrew Duberstein Andrew Kondrich Andrey Mishchenko Andy Applebaum Angela Jiang Ashvin Nair Barret Zoph Behrooz Ghorbani Ben Rossen Benjamin Sokolowsky Boaz Barak Bob McGrew Borys Minaiev Botao Hao Bowen Baker Brandon Houghton Brandon McKinzie Brydon Eastman Camillo Lugaresi Cary Bassin Cary Hudson Chak Ming Li Charles de Bourcy Chelsea Voss Chen Shen Chong Zhang Chris Koch Chris Orsinger Christopher Hesse Claudia Fischer Clive Chan Dan Roberts Daniel Kappler Daniel Levy Daniel Selsam David Dohan David Farhi David Mely David Robinson Dimitris Tsipras Doug Li Dragos Oprica Eben Freeman Eddie Zhang Edmund Wong Elizabeth Proehl Enoch Cheung Eric Mitchell Eric Wallace Erik Ritter Evan Mays Fan Wang Felipe Petroski Such Filippo Raso Florencia Leoni Foivos Tsimpourlas Francis Song Fred von Lohmann Freddie Sulit Geoff Salmon Giambattista Parascandolo Gildas Chabot Grace Zhao Greg Brockman Guillaume Leclerc Hadi Salman Haiming Bao Hao Sheng Hart Andrin Hessam Bagherinezhad Hongyu Ren Hunter Lightman Hyung Won Chung Ian Kivlichan Ian O'Connell Ian Osband Ignasi Clavera Gilaberte Ilge Akkaya Ilya Kostrikov Ilya Sutskever Irina Kofman Jakub Pachocki James Lennon Jason Wei Jean Harb Jerry Twore Jiacheng Feng Jiahui Yu Jiayi Weng Jie Tang Jieqi Yu Joaquin Qui\u00f1onero Candela Joe Palermo Joel Parish Johannes Heidecke John Hallman John Rizzo Jonathan Gordon Jonathan Uesato Jonathan Ward Joost Huizinga Julie Wang Kai Chen Kai Xiao Karan Singhal Karina Nguyen Karl Cobbe Katy Shi Kayla Wood Kendra Rimbach Keren Gu-Lemberg Kevin Liu Kevin Lu Kevin Stone Kevin Yu Lama Ahmad Lauren Yang Leo Liu Leon Maksin Leyton Ho Liam Fedus Lilian Weng Linden Li Lindsay McCallum Lindsey Held Lorenz Kuhn Lukas Kondraciuk Lukasz Kaiser Luke Metz Madelaine Boyd Maja Trebacz Manas Joglekar Mark Chen Marko Tintor Mason Meyer Matt Jones Matt Kaufer Max Schwarzer Meghan Shah Mehmet Yatbaz Melody Y. Guan Mengyuan Xu Mengyuan Yan Mia Glaese Mianna Chen Michael Lampe Michael Malek Michele Wang Michelle Fradin Mike McClay Mikhail Pavlov Miles Wang Mingxuan Wang Mira Murati Mo Bavarian Mostafa Rohaninejad Nat McAleese Neil Chowdhury Neil Chowdhury Nick Ryder Nikolas Tezak Noam Brown Ofir Nachum Oleg Boiko Oleg Murk Olivia Watkins Patrick Chao Paul Ashbourne Pavel Izmailov Peter Zhokhov Rachel Dias Rahul Arora Randall Lin Rapha Gontijo Lopes Raz Gaon Reah Miyara Reimar Leike Renny Hwang Rhythm Garg Robin Brown Roshan James Rui Shu Ryan Cheu Ryan Greene Saachi Jain Sam Altman Sam Toizer Sam Toyer Samuel Miserendino Sandhini Agarwal Santiago Hernandez Sasha Baker Scott McKinney Scottie Yan Shengjia Zhao Shengli Hu Shibani Santurkar Shraman Ray Chaudhuri Shuyuan Zhang Siyuan Fu Spencer Papay Steph Lin Suchir Balaji Suvansh Sanjeev Szymon Sidor Tal Broda Aidan Clark Tao Wang Taylor Gordon Ted Sanders Tejal Patwardhan Thibault Sottiaux Thomas Degry Thomas Dimson Tianhao Zheng Timur Garipov Tom Stasi Trapit Bansal Trevor Creech Troy Peterson Tyna Eloundou Valerie Qi Vineet Kosaraju Vinnie Monaco Vitchyr Pong Vlad Fomenko Weiyi Zheng Wenda Zhou Wes McCabe Wojciech Zaremba Yann Dubois Yinghai Lu Yining Chen Young Cha Yu Bai Yuchen He Yuchen Zhang Yunyun Wang Zheng Shao and Zhuohan Li. 2024. OpenAI o1 System Card. arXiv:2412.16720 [cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_2_1_25_1","unstructured":"Onat Ozer Grace Wu Yuchen Wang Daniel Dosti Honghao Zhang and Vivi De La Rue. 2025. MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs. arXiv:2512.20845 [cs.AI] https:\/\/arxiv.org\/abs\/2512.20845"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445618"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203431900"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463242"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_2_1_30_1","unstructured":"Herbert A. Simon. 1978. Information-Processing Theory of Human Problem Solving. https:\/\/api.semanticscholar.org\/CorpusID:10344827"},{"key":"e_1_3_2_1_31_1","unstructured":"Kimi Team Angang Du Bofei Gao Bowei Xing Changjiu Jiang Cheng Chen Cheng Li Chenjun Xiao Chenzhuang Du Chonghua Liao Chuning Tang Congcong Wang Dehao Zhang Enming Yuan Enzhe Lu Fengxiang Tang Flood Sung Guangda Wei Guokun Lai Haiqing Guo Han Zhu Hao Ding Hao Hu Hao Yang Hao Zhang Haotian Yao Haotian Zhao Haoyu Lu Haoze Li Haozhen Yu Hongcheng Gao Huabin Zheng Huan Yuan Jia Chen Jianhang Guo Jianlin Su Jianzhou Wang Jie Zhao Jin Zhang Jingyuan Liu Junjie Yan Junyan Wu Lidong Shi Ling Ye Longhui Yu Mengnan Dong Neo Zhang Ningchen Ma Qiwei Pan Qucheng Gong Shaowei Liu Shengling Ma Shupeng Wei Sihan Cao Siying Huang Tao Jiang Weihao Gao Weimin Xiong Weiran He Weixiao Huang Weixin Xu Wenhao Wu Wenyang He Xianghui Wei Xianqing Jia Xingzhe Wu Xinran Xu Xinxing Zu Xinyu Zhou Xuehai Pan Y. Charles Yang Li Yangyang Hu Yangyang Liu Yanru Chen Yejie Wang Yibo Liu Yidao Qin Yifeng Liu Ying Yang Yiping Bao Yulun Du Yuxin Wu Yuzhi Wang Zaida Zhou Zhaoji Wang Zhaowei Li Zhen Zhu Zheng Zhang Zhexu Wang Zhilin Yang Zhiqi Huang Zihao Huang Ziyao Xu Zonghan Yang and Zongyu Lin. 2025. Kimi k1.5: Scaling Reinforcement Learning with LLMs. arXiv:2501.12599 [cs.AI] https:\/\/arxiv.org\/abs\/2501.12599"},{"key":"e_1_3_2_1_32_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:2504.12516 [cs.CL] https:\/\/arxiv.org\/abs\/2504.12516"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.508"},{"key":"e_1_3_2_1_34_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_35_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_36_1","unstructured":"Siyu Yuan Zehui Chen Zhiheng Xi Junjie Ye Zhengyin Du and Jiecao Chen. 2025. Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training. arXiv:2501.11425 [cs.AI] https:\/\/arxiv.org\/abs\/2501.11425"},{"key":"e_1_3_2_1_37_1","unstructured":"Jingtao Zhan Jiahao Zhao Jiayu Li Yiqun Liu Bo Zhang Qingyao Ai Jiaxin Mao Hongning Wang Min Zhang and Shaoping Ma. 2025. Evaluating Intelligence via Trial and Error. arXiv:2502.18858 [cs.AI] https:\/\/arxiv.org\/abs\/2502.18858"},{"key":"e_1_3_2_1_38_1","unstructured":"Yanzhao Zhang Mingxin Li Dingkun Long Xin Zhang Huan Lin Baosong Yang Pengjun Xie An Yang Dayiheng Liu Junyang Lin Fei Huang and Jingren Zhou. 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv:2506.05176 [cs.CL] https:\/\/arxiv.org\/abs\/2506.05176"},{"key":"e_1_3_2_1_39_1","unstructured":"Shuyan Zhou Frank F. Xu Hao Zhu Xuhui Zhou Robert Lo Abishek Sridhar Xianyi Cheng Tianyue Ou Yonatan Bisk Daniel Fried Uri Alon and Graham Neubig. 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. arXiv:2307.13854 [cs.AI] https:\/\/arxiv.org\/abs\/2307.13854"}],"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":"2026-07-15T17:17:35Z","timestamp":1784135855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":39,"alternative-id":["10.1145\/3805712.3808611","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808611","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"}}]}}