{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:41Z","timestamp":1786120841086,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation, Singapore under its AI Singapore Programme","award":["AISG-NMLP-2024-003"],"award-info":[{"award-number":["AISG-NMLP-2024-003"]}]},{"name":"National Research Foundation, Singapore and Infocomm Media Development Authority under its Trust Tech Funding Initiative","award":["DTC-RGC-05"],"award-info":[{"award-number":["DTC-RGC-05"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817981","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"2897-2908","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2219-4833","authenticated-orcid":false,"given":"Yuyang","family":"Li","sequence":"first","affiliation":[{"name":"CFAR, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore and National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0489-2639","authenticated-orcid":false,"given":"Yiran","family":"Dou","sequence":"additional","affiliation":[{"name":"CFAR, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore and National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8107-114X","authenticated-orcid":false,"given":"Jie-Jing","family":"Shao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-2121","authenticated-orcid":false,"given":"Yueming","family":"Lyu","sequence":"additional","affiliation":[{"name":"CFAR, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8095-4637","authenticated-orcid":false,"given":"Ivor","family":"Tsang","sequence":"additional","affiliation":[{"name":"CFAR, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore and Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9576-9398","authenticated-orcid":false,"given":"Haiyan","family":"Yin","sequence":"additional","affiliation":[{"name":"CFAR, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Twelfth International Conference on Learning Representations (ICLR","author":"Cai Tianle","year":"2024","unstructured":"Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, and Denny Zhou. 2024. Large Language Models as Tool Makers. In The Twelfth International Conference on Learning Representations (ICLR 2024). https:\/\/openreview.net\/forum?id=qV83K9d5WB"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Silin Chen Shaoxin Lin Xiaodong Gu Yuling Shi Heng Lian Longfei Yun Dong Chen Weiguo Sun Lin Cao and Qianxiang Wang. 2025. SWE-Exp: Experience-Driven Software Issue Resolution. http:\/\/arxiv.org\/abs\/2507.23361 arXiv preprint arXiv:2507.23361.","DOI":"10.2139\/ssrn.7234653"},{"key":"e_1_3_2_1_3_1","volume-title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory. arXiv preprint arXiv:2504.19413","author":"Chhikara Prateek","year":"2025","unstructured":"Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory. arXiv preprint arXiv:2504.19413 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS","volume":"36","author":"Deng Xiang","year":"2024","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. Mind2web: Towards a Generalist Agent for the Web. In Advances in Neural Information Processing Systems (NeurIPS 2023), Vol. V36."},{"key":"e_1_3_2_1_5_1","volume-title":"Tom Marty, L\u00e9o Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste.","author":"Drouin Alexandre","year":"2024","unstructured":"Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, L\u00e9o Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. 2024. WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks? arXiv:2403.07718 [cs.LG] https:\/\/arxiv.org\/abs\/2403.07718"},{"key":"e_1_3_2_1_6_1","volume-title":"Luke Hewitt, Armando Solar-Lezama, and Joshua B. Tenenbaum.","author":"Ellis Kevin","year":"2023","unstructured":"Kevin Ellis, Lionel Wong, Maxwell Nye, Mathias Sable-Meyer, Luc Cary, Lore Anaya Pozo, Luke Hewitt, Armando Solar-Lezama, and Joshua B. Tenenbaum. 2023. Dreamcoder: Growing Generalizable, Interpretable Knowledge with Wake\u2013Sleep Bayesian Program Learning. Philosophical Transactions of the Royal Society A, V381, 2251 (2023), 20220050."},{"key":"e_1_3_2_1_7_1","volume-title":"Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang.","author":"Fang Runnan","year":"2025","unstructured":"Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu Manager, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang. 2025. Memp: Exploring Agent Procedural Memory. https:\/\/arxiv.org\/abs\/2508.06433 arXiv preprint arXiv:2508.06433."},{"key":"e_1_3_2_1_8_1","volume-title":"The Twelfth International Conference on Learning Representations (ICLR","author":"Grand Gabriel","year":"2024","unstructured":"Gabriel Grand, Lionel Wong, Matthew Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, and Jacob Andreas. 2024. LILO: Learning Interpretable Libraries by Compressing and Documenting Code. In The Twelfth International Conference on Learning Representations (ICLR 2024). https:\/\/openreview.net\/forum?id=TqYbAWKMIe"},{"key":"e_1_3_2_1_9_1","volume-title":"Hiagent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model. https:\/\/arxiv.org\/abs\/2408.09559 arXiv preprint arXiv:2408.09559.","author":"Hu Mengkang","year":"2024","unstructured":"Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, and Ping Luo. 2024. Hiagent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model. https:\/\/arxiv.org\/abs\/2408.09559 arXiv preprint arXiv:2408.09559."},{"key":"e_1_3_2_1_10_1","unstructured":"Minqi Jiang Andrei Lupu and Yoram Bachrach. 2025. Bootstrapping Task Spaces for Self-Improvement. https:\/\/arxiv.org\/abs\/2509.04575 arXiv preprint arXiv:2509.04575."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"e_1_3_2_1_12_1","volume-title":"Manning","author":"Murty Shikhar","year":"2024","unstructured":"Shikhar Murty, Dzmitry Bahdanau, and Christopher D. Manning. 2024a. Nnetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator. https:\/\/arxiv.org\/abs\/2410.02907 arXiv preprint arXiv:2410.02907."},{"key":"e_1_3_2_1_13_1","volume-title":"Bagel: Bootstrapping Agents by Guiding Exploration with Language. https:\/\/arxiv.org\/abs\/2403.08140 arXiv preprint arXiv:2403.08140.","author":"Murty Shikhar","year":"2024","unstructured":"Shikhar Murty, Christopher Manning, Peter Shaw, Mandar Joshi, and Kenton Lee. 2024b. Bagel: Bootstrapping Agents by Guiding Exploration with Language. https:\/\/arxiv.org\/abs\/2403.08140 arXiv preprint arXiv:2403.08140."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2908"},{"key":"e_1_3_2_1_15_1","volume-title":"Reasoningbank: Scaling Agent Self-Evolving with Reasoning Memory. https:\/\/arxiv.org\/abs\/2509.25140 arXiv preprint arXiv:2509.25140.","author":"Ouyang Siru","year":"2025","unstructured":"Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, et al., 2025. Reasoningbank: Scaling Agent Self-Evolving with Reasoning Memory. https:\/\/arxiv.org\/abs\/2509.25140 arXiv preprint arXiv:2509.25140."},{"key":"e_1_3_2_1_16_1","volume-title":"Percy Liang, and Michael S.","author":"Park Joon Sung","year":"2023","unstructured":"Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. https:\/\/arxiv.org\/abs\/2304.03442 arXiv preprint arXiv:2304.03442."},{"key":"e_1_3_2_1_17_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oVKEAFjEqv","author":"Qi Zehan","year":"2025","unstructured":"Zehan Qi, Xiao Liu, et al., 2025. WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oVKEAFjEqv"},{"key":"e_1_3_2_1_18_1","volume-title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve. https:\/\/arxiv.org\/abs\/2407.18219 arXiv preprint arXiv:2407.18219.","author":"Qu Yuxiao","year":"2024","unstructured":"Yuxiao Qu, Tianjun Zhang, Naman Garg, and Aviral Kumar. 2024. Recursive Introspection: Teaching Language Model Agents How to Self-Improve. https:\/\/arxiv.org\/abs\/2407.18219 arXiv preprint arXiv:2407.18219."},{"key":"e_1_3_2_1_19_1","volume-title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought. Advances in Neural Information Processing Systems (NeurIPS","author":"Sarch Gabriel","year":"2024","unstructured":"Gabriel Sarch, Lawrence Jang, Michael Tarr, William W. Cohen, Kenneth Marino, and Katerina Fragkiadaki. 2024. VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought. Advances in Neural Information Processing Systems (NeurIPS 2024), V37 (2024), 75942-75985."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 43rd International Conference on Machine Learning.","author":"Shao Jie-Jing","year":"2026","unstructured":"Jie-Jing Shao, Haiyan Yin, Yueming Lyu, Xingrui Yu, Lan-Zhe Guo, Ivor Tsang, James Kwok, and Yu-Feng Li. 2026. Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks. In Proceedings of the 43rd International Conference on Machine Learning."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.120"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Junhong Shen Hao Bai Lunjun Zhang Yifei Zhou Amrith Setlur Shengbang Tong Diego Caples Nan Jiang Tong Zhang Ameet Talwalkar and Aviral Kumar. 2025. Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction. http:\/\/arxiv.org\/abs\/2506.07976 arXiv preprint arXiv:2506.07976.","DOI":"10.52202\/085713-5647"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS","volume":"32","author":"Shin Eui Chul","year":"2019","unstructured":"Eui Chul Shin, Miltiadis Allamanis, Marc Brockschmidt, and Alex Polozov. 2019. Program Synthesis and Semantic Parsing with Learned Code Idioms. In Advances in Neural Information Processing Systems (NeurIPS 2019), Vol. V32."},{"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","volume-title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","author":"Wang Guanzhi","year":"2023","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An Open-Ended Embodied Agent with Large Language Models. http:\/\/arxiv.org\/abs\/2305.16291 arXiv preprint arXiv:2305.16291."},{"key":"e_1_3_2_1_26_1","volume-title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks. In Forty-first International Conference on Machine Learning (ICML","author":"Wang Zhiruo","year":"2024","unstructured":"Zhiruo Wang, Graham Neubig, and Daniel Fried. 2024. TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks. In Forty-first International Conference on Machine Learning (ICML 2024). https:\/\/openreview.net\/forum?id=DCNCwaMJjI"},{"key":"e_1_3_2_1_27_1","volume-title":"Inducing Programmatic Skills for Agentic Tasks. In Second Conference on Language Modeling. https:\/\/openreview.net\/forum?id=lsAY6fWsog","author":"Wang Zora Zhiruo","year":"2025","unstructured":"Zora Zhiruo Wang, Apurva Gandhi, Graham Neubig, and Daniel Fried. 2025a. Inducing Programmatic Skills for Agentic Tasks. In Second Conference on Language Modeling. https:\/\/openreview.net\/forum?id=lsAY6fWsog"},{"key":"e_1_3_2_1_28_1","volume-title":"Agent Workflow Memory. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=NTAhi2JEEE","author":"Wang Zora Zhiruo","year":"2025","unstructured":"Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2025b. Agent Workflow Memory. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=NTAhi2JEEE"},{"key":"e_1_3_2_1_29_1","volume-title":"The Twelfth International Conference on Learning Representations (ICLR","author":"Wong Lionel","year":"2024","unstructured":"Lionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, and Jacob Andreas. 2024. Learning Grounded Action Abstractions from Language. In The Twelfth International Conference on Learning Representations (ICLR 2024). https:\/\/openreview.net\/forum?id=qJ0Cfj4Ex9"},{"key":"e_1_3_2_1_30_1","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR","author":"Xu Yiheng","year":"2025","unstructured":"Yiheng Xu, Dunjie Lu, Zhennan Shen, Junli Wang, Zekun Wang, Yuchen Mao, Caiming Xiong, and Tao Yu. 2025. Agenttrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials. In The Thirteenth International Conference on Learning Representations (ICLR 2025). https:\/\/openreview.net\/forum?id=EEgYUccwsV"},{"key":"e_1_3_2_1_31_1","unstructured":"Tianci Xue Weijian Qi et al. 2025. An Illusion of Progress? Assessing the Current State of Web Agents. https:\/\/arxiv.org\/abs\/2504.01382 arXiv preprint arXiv:2504.01382."},{"key":"e_1_3_2_1_32_1","volume-title":"AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oWdzUpOlkX","author":"Yang Ke","year":"2025","unstructured":"Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, and Huzefa Rangwala. 2025a. AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=oWdzUpOlkX"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1195"},{"key":"e_1_3_2_1_34_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/arxiv.org\/pdf\/2210","author":"Yao Shunyu","year":"2023","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. In The Eleventh International Conference on Learning Representations. https:\/\/arxiv.org\/pdf\/2210.03629"},{"key":"e_1_3_2_1_35_1","unstructured":"Simon Yu Gang Li Weiyan Shi and Peng Qi. 2025. PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction. arXiv:2510.15863 [cs.CL] https:\/\/arxiv.org\/abs\/2510.15863"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34505"},{"key":"e_1_3_2_1_37_1","volume-title":"Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, and Yu Su.","author":"Zheng Boyuan","year":"2025","unstructured":"Boyuan Zheng, Michael Y. Fatemi, Xiaolong Jin, Zora Zhiruo Wang, Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, and Yu Su. 2025. SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills. https:\/\/arxiv.org\/abs\/2504.07079 arXiv preprint arXiv:2504.07079."},{"key":"e_1_3_2_1_38_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. 2024a. WebArena: A Realistic Web Environment for Building Autonomous Agents. arXiv:2307.13854 [cs.AI] https:\/\/arxiv.org\/abs\/2307.13854"},{"key":"e_1_3_2_1_39_1","unstructured":"Yifei Zhou Qianlan Yang Kaixiang Lin Min Bai Xiong Zhou Yu-Xiong Wang Sergey Levine and Erran Li. 2024b. Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents. http:\/\/arxiv.org\/abs\/2412.13194 arXiv preprint arXiv:2412.13194."},{"key":"e_1_3_2_1_40_1","volume-title":"Oagents: An Empirical Study of Building Effective Agents. https:\/\/arxiv.org\/abs\/2506.15741 arXiv preprint arXiv:2506.15741.","author":"Zhu He","year":"2025","unstructured":"He Zhu, Tianrui Qin, King Zhu, et al., 2025. Oagents: An Empirical Study of Building Effective Agents. https:\/\/arxiv.org\/abs\/2506.15741 arXiv preprint arXiv:2506.15741."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:17:48Z","timestamp":1786065468000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817981"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":40,"alternative-id":["10.1145\/3770855.3817981","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817981","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}