{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ad-agent-a-multi-agent-framework-for-end-to","title":"AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection","arxiv_id":"2505.12594","date":"2025-05-19","proceeding":null,"authors":["Tiankai Yang","Junjun Liu","Wingchun Siu","Jiahang Wang","Zhuangzhuang Qian","Chanjuan Song","Cheng Cheng","Xiyang Hu","Yue Zhao"],"abstract":"Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for non-expert users who lack in-depth library-specific knowledge and advanced programming skills. To tackle this, we present AD-AGENT, an LLM-driven multi-agent framework that turns natural-language instructions into fully executable AD pipelines. AD-AGENT coordinates specialized agents for intent parsing, data preparation, library and model selection, documentation mining, and iterative code generation and debugging. Using a shared short-term workspace and a long-term cache, the agents integrate popular AD libraries like PyOD, PyGOD, and TSLib into a unified workflow. Experiments demonstrate that AD-AGENT produces reliable scripts and recommends competitive models across libraries. The system is open-sourced to support further research and practical applications in AD.","url_abs":"https://arxiv.org/abs/2505.12594v1","url_pdf":"https://arxiv.org/pdf/2505.12594v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ad-agent-a-multi-agent-framework-for-end-to","repo_url":"https://github.com/usc-fortis/ad-agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"fraud-detection","task_name":"Fraud Detection"},{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.12594","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}