Ensuring security in wireless ad hoc networks is absolutely necessary and a must for any securitycritical applications. In this paper, we report our progress in the development of an agent-based cooperative anomaly detection scheme for wireless ad hoc networks. The approach addresses the underlying distributed and cooperative nature of wireless ad hoc networks and adds one more dimension of cooperation to the intrusion detection process. That is, the anomaly detection is performed in a cooperative way involving the participation of multiple mobile nodes. Unlike traditional signature-based misuse detection approaches, the proposed scheme detects various types of intrusions/attacks based on the model learned only from normal network behaviors. Without the requirements of pre-labeled attack data, the approach eliminates the time-consuming labeling process and the impacts of imbalanced dataset. Besides, the concept of software agent technology has been applied in system implementation, which provides further support for distributed wireless ad hoc networks.