{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:42Z","timestamp":1786120842791,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":64,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818652","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"13245-13251","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Recipes for Agents: Understanding Skills and Their Open Questions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3481-1146","authenticated-orcid":false,"given":"Hanwen","family":"Xing","sequence":"first","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7501-3154","authenticated-orcid":false,"given":"Haomin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5976-0360","authenticated-orcid":false,"given":"Xuandong","family":"Zhao","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-7972","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8769-9974","authenticated-orcid":false,"given":"Zhenheng","family":"Tang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, HONGKONG, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-5665","authenticated-orcid":false,"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106267"},{"key":"e_1_3_2_1_2_1","unstructured":"Dario Amodei. 2023. Dario Amodei (Anthropic CEO) - $10 Billion Models OpenAI Scaling & AGI in 2 years. Dwarkesh Podcast. https:\/\/www.dwarkesh.com\/p\/dario-amodei"},{"key":"e_1_3_2_1_3_1","volume-title":"State of AI: An Empirical 100 Trillion Token Study with OpenRouter. arXiv preprint arXiv:2601.10088","author":"Aubakirova Malika","year":"2026","unstructured":"Malika Aubakirova, Alex Atallah, Chris Clark, Justin Summerville, and Anjney Midha. 2026. State of AI: An Empirical 100 Trillion Token Study with OpenRouter. arXiv preprint arXiv:2601.10088 (2026)."},{"key":"e_1_3_2_1_4_1","volume-title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions. arXiv preprint arXiv:2505.23281","author":"Balunovi\u00e7 Mislav","year":"2025","unstructured":"Mislav Balunovi\u00e7, Jasper Dekoninck, Ivo Petrov, Nikola Jovanovi\u00e7, and Martin Vechev. 2025. MathArena: Evaluating LLMs on Uncontaminated Math Competitions. arXiv preprint arXiv:2505.23281 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2018.09.016"},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al., 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems (NeurIPS), Vol. V33. 1877-1901."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.5317da47"},{"key":"e_1_3_2_1_8_1","volume-title":"Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents. Advances in Neural Information Processing Systems, V37","author":"Debenedetti Edoardo","year":"2024","unstructured":"Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, and Florian Tram\u00e8r. 2024. Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents. Advances in Neural Information Processing Systems, V37 (2024), 82895-82920."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9589-y"},{"key":"e_1_3_2_1_10_1","unstructured":"Nadia Eghbal. 2016. Roads and Bridges: The Unseen Labor Behind Our Digital Infrastructure."},{"key":"e_1_3_2_1_11_1","volume-title":"Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web. Transactions on Machine Learning Research","author":"Furuta Hiroki","year":"2024","unstructured":"Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust, and Izzeddin Gur. 2024. Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web. Transactions on Machine Learning Research (2024). arXiv:2311.18751."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML).","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, et al., 2023. PAL: Program-Aided Language Models. In Proceedings of the 40th International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_13_1","volume-title":"Jae Jun Lee, and Gwang Ho Baik.","author":"Gong Eun Jeong","year":"2025","unstructured":"Eun Jeong Gong, Chang Seok Bang, Jae Jun Lee, and Gwang Ho Baik. 2025. Knowledge-Practice Performance Gap in Clinical Large Language Models: Systematic Review of 39 Benchmarks. Journal of Medical Internet Research (2025). Article e84120."},{"key":"e_1_3_2_1_14_1","volume-title":"Chu","author":"Goodell Alex J.","year":"2025","unstructured":"Alex J. Goodell, Simon N. Chu, Dara Rouholiman, and Larry F. Chu. 2025. Large language model agents can use tools to perform clinical calculations. npj Digital Medicine, V8 (2025), 163."},{"key":"e_1_3_2_1_15_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Peiyi Wang Qihao Zhu Runxin Xu Ruoyu Zhang Shirong Ma 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_16_1","unstructured":"Taicheng Guo Xiuying Chen Yaqi Wang Ruidi Chang Shichao Pei Nitesh V Chawla Olaf Wiest and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. In IJCAI."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 48th IEEE\/ACM International Conference on Software Engineering (ICSE). arXiv:2412","author":"He Hao","year":"2026","unstructured":"Hao He, Haoqin Yang, Philipp Burckhardt, et al., 2026. Six Million (Suspected) Fake Stars in GitHub: A Growing Spiral of Popularity Contests, Spams, and Malware. In Proceedings of the 48th IEEE\/ACM International Conference on Software Engineering (ICSE). arXiv:2412.13459."},{"key":"e_1_3_2_1_18_1","volume-title":"Context Rot: How Increasing Input Tokens Impacts LLM Performance. https:\/\/research.trychroma.com\/context-rot Technical report, Chroma Research.","author":"Hong Kelly","year":"2025","unstructured":"Kelly Hong, Anton Troynikov, and Jeff Huber. 2025. Context Rot: How Increasing Input Tokens Impacts LLM Performance. https:\/\/research.trychroma.com\/context-rot Technical report, Chroma Research."},{"key":"e_1_3_2_1_19_1","volume-title":"Procedural Knowledge Improves Agentic LLM Workflows. arXiv preprint arXiv:2511.07568","author":"Hsiao Vincent","year":"2025","unstructured":"Vincent Hsiao, Mark Roberts, and Leslie Smith. 2025. Procedural Knowledge Improves Agentic LLM Workflows. arXiv preprint arXiv:2511.07568 (2025)."},{"key":"e_1_3_2_1_20_1","volume-title":"Does math reasoning improve general LLM capabilities? understanding transferability of llm reasoning. arXiv preprint arXiv:2507.00432","author":"Huan Maggie","year":"2025","unstructured":"Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, and Xiang Yue. 2025. Does math reasoning improve general LLM capabilities? understanding transferability of llm reasoning. arXiv preprint arXiv:2507.00432 (2025)."},{"key":"e_1_3_2_1_21_1","unstructured":"Yue Huang Chujie Gao Siyuan Wu Haoran Wang Xiangqi Wang Yujun Zhou Yanbo Wang Jiayi Ye Jiawen Shi Qihui Zhang et al. 2025. On the trustworthiness of generative foundation models: Guideline assessment and perspective. arXiv preprint arXiv:2502.14296 (2025)."},{"key":"e_1_3_2_1_22_1","unstructured":"Yue Huang Lichao Sun Haoran Wang Siyuan Wu Qihui Zhang Yuan Li Chujie Gao Yixin Huang Wenhan Lyu Yixuan Zhang et al. 2024. TrustLLM: Trustworthiness in large language models. arXiv preprint arXiv:2401.05561 (2024)."},{"key":"e_1_3_2_1_23_1","unstructured":"Invariant Labs. 2025. MCP Security Notification: Tool Poisoning Attacks. https:\/\/invariantlabs.ai\/blog\/mcp-security-notification-tool-poisoning-attacks"},{"key":"e_1_3_2_1_24_1","volume-title":"SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement. arXiv preprint arXiv:2602.14211","author":"Jia Xiaojun","year":"2026","unstructured":"Xiaojun Jia, Jie Liao, Simeng Qin, Jindong Gu, Wenqi Ren, Xiaochun Cao, Yang Liu, and Philip Torr. 2026. SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement. arXiv preprint arXiv:2602.14211 (2026)."},{"key":"e_1_3_2_1_25_1","volume-title":"Artificial hivemind: The open-ended homogeneity of language models (and beyond). arXiv preprint arXiv:2510.22954","author":"Jiang Liwei","year":"2025","unstructured":"Liwei Jiang, Yuanjun Chai, Margaret Li, Mickel Liu, Raymond Fok, Nouha Dziri, Yulia Tsvetkov, Maarten Sap, Alon Albalak, and Yejin Choi. 2025. Artificial hivemind: The open-ended homogeneity of language models (and beyond). arXiv preprint arXiv:2510.22954 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"SoK: Agentic Skills-Beyond Tool Use in LLM Agents. arXiv preprint arXiv:2602.20867","author":"Jiang Yanna","year":"2026","unstructured":"Yanna Jiang, Delong Li, Haiyu Deng, Baihe Ma, Xu Wang, Qin Wang, and Guangsheng Yu. 2026. SoK: Agentic Skills-Beyond Tool Use in LLM Agents. arXiv preprint arXiv:2602.20867 (2026)."},{"key":"e_1_3_2_1_27_1","volume-title":"The Twelfth International Conference on Learning Representations (ICLR).","author":"Jimenez Carlos E.","year":"2024","unstructured":"Carlos E. Jimenez, John Yang, Alexander Wettig, et al., 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues?. In The Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.324"},{"key":"e_1_3_2_1_29_1","unstructured":"LabRAI. 2026. LangSkills: A Collection of Language Model Skills. https:\/\/github.com\/LabRAI\/LangSkills. GitHub repository."},{"key":"e_1_3_2_1_30_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. In NeurIPS."},{"key":"e_1_3_2_1_31_1","volume-title":"2026 b. Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale. arXiv preprint arXiv:2603.02176","author":"Li Hao","year":"2026","unstructured":"Hao Li, Chunjiang Mu, Jianhao Chen, Siyue Ren, Zhiyao Cui, Yiqun Zhang, Lei Bai, and Shuyue Hu. 2026 b. Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale. arXiv preprint arXiv:2603.02176 (2026)."},{"key":"e_1_3_2_1_32_1","unstructured":"Xiangyi Li Wenbo Chen Yimin Liu Shenghan Zheng et al. 2026 a. SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks. arXiv preprint arXiv:2602.12670 (2026)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44336-024-00009-2"},{"key":"e_1_3_2_1_34_1","unstructured":"Xixun Lin Yucheng Ning Jingwen Zhang Yan Dong Yilong Liu Yongxuan Wu Xiaohua Qi Nan Sun Yanmin Shang Kun Wang et al. 2025. LLM-based agents suffer from hallucinations: A survey of taxonomy methods and directions. arXiv preprint arXiv:2509.18970 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality. arXiv preprint arXiv:2602.08004","author":"Ling George","year":"2026","unstructured":"George Ling, Shanshan Zhong, and Richard Huang. 2026. Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality. arXiv preprint arXiv:2602.08004 (2026)."},{"key":"e_1_3_2_1_36_1","volume-title":"2026 a. Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study. arXiv preprint arXiv:2602.06547","author":"Liu Yi","year":"2026","unstructured":"Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, and Leo Yu Zhang. 2026 a. Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study. arXiv preprint arXiv:2602.06547 (2026)."},{"key":"e_1_3_2_1_37_1","volume-title":"2026 b. Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale. arXiv preprint arXiv:2601.10338","author":"Liu Yi","year":"2026","unstructured":"Yi Liu, Weizhe Wang, Ruitao Feng, Yao Zhang, Guangquan Xu, Gelei Deng, Yuekang Li, and Leo Zhang. 2026 b. Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale. arXiv preprint arXiv:2601.10338 (2026)."},{"key":"e_1_3_2_1_38_1","volume-title":"FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models. arXiv preprint arXiv:2501.18062","author":"Mateega Spencer","year":"2025","unstructured":"Spencer Mateega, Carlos Georgescu, and Danny Tang. 2025. FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models. arXiv preprint arXiv:2501.18062 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools. arXiv preprint arXiv:2508.02110","author":"Mo Kanghua","year":"2025","unstructured":"Kanghua Mo, Li Hu, Yucheng Long, and Zhihao Li. 2025. Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools. arXiv preprint arXiv:2508.02110 (2025)."},{"key":"e_1_3_2_1_40_1","volume-title":"Synthelite: Chemist-Aligned and Feasibility-Aware Synthesis Planning with LLMs. arXiv preprint arXiv:2512.16424","author":"Nguyen Xuan-Vu","year":"2025","unstructured":"Xuan-Vu Nguyen, Daniel Armstrong, Milena Wehrbach, Andres M Bran, Zlatko Joncev, and Philippe Schwaller. 2025. Synthelite: Chemist-Aligned and Feasibility-Aware Synthesis Planning with LLMs. arXiv preprint arXiv:2512.16424 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807763"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.45"},{"key":"e_1_3_2_1_43_1","volume-title":"Toolformer: Language Models Can Teach Themselves to Use Tools. NeurIPS","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. NeurIPS (2023)."},{"key":"e_1_3_2_1_44_1","unstructured":"David Schmotz et al. 2026. Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks. arXiv preprint arXiv:2602.20156 (2026)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 12th International Conference on Learning Representations (ICLR).","author":"Sclar Melanie","year":"2024","unstructured":"Melanie Sclar, Yejin Choi, Yulia Tsvetkov, and Alane Suhr. 2024. Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design. In Proceedings of the 12th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_46_1","volume-title":"Electric Dogs, and General Relativity. arXiv preprint arXiv:2512.20264","author":"Shukla Hemant","year":"2025","unstructured":"Hemant Shukla. 2025. The AI Scaling Wall of Diminishing Returns: Of LLMs, Electric Dogs, and General Relativity. arXiv preprint arXiv:2512.20264 (2025)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07566-y"},{"key":"e_1_3_2_1_48_1","volume-title":"10th Annual State of the Software Supply Chain Report. https:\/\/www.sonatype.com\/state-of-the-software-supply-chain\/2024\/scale","unstructured":"Sonatype. 2024. 10th Annual State of the Software Supply Chain Report. https:\/\/www.sonatype.com\/state-of-the-software-supply-chain\/2024\/scale"},{"key":"e_1_3_2_1_49_1","volume-title":"Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models. Transactions on Machine Learning Research","author":"Aarohi Srivastava","year":"2023","unstructured":"Aarohi Srivastava et al., 2023. Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Learnware of Language Models: Specialized Small Language Models Can Do Big. arXiv preprint arXiv:2505.13425","author":"Tan Zhi-Hao","year":"2025","unstructured":"Zhi-Hao Tan, Zi-Chen Zhao, Hao-Yu Shi, Xin-Yu Zhang, Peng Tan, Yang Yu, and Zhi-Hua Zhou. 2025. Learnware of Language Models: Specialized Small Language Models Can Do Big. arXiv preprint arXiv:2505.13425 (2025)."},{"key":"e_1_3_2_1_51_1","unstructured":"Tidelift. 2024. 2024 State of the Open Source Maintainer Report. https:\/\/www.tidelift.com\/open-source-maintainer-survey-2024"},{"key":"e_1_3_2_1_52_1","volume-title":"Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research","author":"Wang Guanzhi","year":"2024","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, et al., 2024. Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Zhichao Xu, Megha Gandhi, Panpan Xu, and Lin Lee Cheong.","author":"Wang Jiongxiao","year":"2025","unstructured":"Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, and Lin Lee Cheong. 2025b. Reinforcement Learning for Self-Improving Agent with Skill Library. arXiv preprint arXiv:2512.17102 (2025)."},{"key":"e_1_3_2_1_54_1","unstructured":"Zhiqiang Wang et al. 2025a. MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers. arXiv preprint arXiv:2508.14925 (2025)."},{"key":"e_1_3_2_1_55_1","volume-title":"Generative monoculture in large language models. arXiv preprint arXiv:2407.02209","author":"Wu Fan","year":"2024","unstructured":"Fan Wu, Emily Black, and Varun Chandrasekaran. 2024. Generative monoculture in large language models. arXiv preprint arXiv:2407.02209 (2024)."},{"key":"e_1_3_2_1_56_1","volume-title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning. arXiv preprint arXiv:2602.08234","author":"Xia Peng","year":"2026","unstructured":"Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie, and Huaxiu Yao. 2026. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning. arXiv preprint arXiv:2602.08234 (2026)."},{"key":"e_1_3_2_1_57_1","volume-title":"Improving the Efficiency of LLM Agent Systems through Trajectory Reduction. arXiv preprint arXiv:2509.23586","author":"Xiao Yuan-An","year":"2025","unstructured":"Yuan-An Xiao, Pengfei Gao, Chao Peng, and Yingfei Xiong. 2025. Improving the Efficiency of LLM Agent Systems through Trajectory Reduction. arXiv preprint arXiv:2509.23586 (2025)."},{"key":"e_1_3_2_1_58_1","volume-title":"Acquisition, Security, and the Path Forward. arXiv preprint arXiv:2602.12430","author":"Xu Renjun","year":"2026","unstructured":"Renjun Xu and Yang Yan. 2026. Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward. arXiv preprint arXiv:2602.12430 (2026)."},{"key":"e_1_3_2_1_59_1","unstructured":"Yutao Yang Junsong Li Qianjun Pan Bihao Zhan Yuxuan Cai Lin Du Jie Zhou Kai Chen Qin Chen Xin Li et al. 2026. AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution. arXiv preprint arXiv:2603.01145 (2026)."},{"key":"e_1_3_2_1_60_1","volume-title":"A Benchmark for Tool-Agent-User Interaction in Real-World Domains. arXiv preprint arXiv:2406.12045","author":"Yao Shunyu","year":"2024","unstructured":"Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. 2024. \u03c4 $-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains. arXiv preprint arXiv:2406.12045 (2024)."},{"key":"e_1_3_2_1_61_1","volume-title":"Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? arXiv preprint arXiv:2504.13837","author":"Yue Yang","year":"2025","unstructured":"Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Shiji Song, and Gao Huang. 2025. Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? arXiv preprint arXiv:2504.13837 (2025)."},{"key":"e_1_3_2_1_62_1","volume-title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents. In Findings of the Association for Computational Linguistics: ACL","author":"Zhan Qiusi","year":"2024","unstructured":"Qiusi Zhan, Zhixiang Liang, Zifan Ying, and Daniel Kang. 2024. InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents. In Findings of the Association for Computational Linguistics: ACL 2024."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00046"},{"key":"e_1_3_2_1_64_1","unstructured":"Shuyan Zhou Frank F. Xu Hao Zhu et al. 2023. WebArena: A Realistic Web Environment for Building Autonomous Agents. arXiv preprint arXiv:2307.13854 (2023)."}],"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":"2026-08-07T01:24:14Z","timestamp":1786065854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":64,"alternative-id":["10.1145\/3770855.3818652","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818652","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"}}]}}