{"ID":2884677,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06189","arxiv_id":"2508.06189","title":"MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration","abstract":"With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on feature recognition struggle to capture high-level behavioral semantics from historical information, while generative approaches based on Large Language Models (LLMs) often fail to meet real-time requirements. To address these challenges, we propose MA-CBP, a criminal behavior prediction framework based on multi-agent asynchronous collaboration. This framework transforms real-time video streams into frame-level semantic descriptions, constructs causally consistent historical summaries, and fuses adjacent image frames to perform joint reasoning over long- and short-term contexts. The resulting behavioral decisions include key elements such as event subjects, locations, and causes, enabling early warning of potential criminal activity. In addition, we construct a high-quality criminal behavior dataset that provides multi-scale language supervision, including frame-level, summary-level, and event-level semantic annotations. Experimental results demonstrate that our method achieves superior performance on multiple datasets and offers a promising solution for risk warning in urban public safety scenarios.","short_abstract":"With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on feature recognition struggle to capture high-level behavioral semantics from historical information, while generative approaches based on Larg...","url_abs":"https://arxiv.org/abs/2508.06189","url_pdf":"https://arxiv.org/pdf/2508.06189v2","authors":"[\"Cheng Liu\",\"Daou Zhang\",\"Tingxu Liu\",\"Yuhan Wang\",\"Jinyang Chen\",\"Yuexuan Li\",\"Xinying Xiao\",\"Chenbo Xin\",\"Ziru Wang\",\"Weichao Wu\"]","published":"2025-08-08T10:12:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}