Advances in spectrum agility for Cognitive Radios (CR) have increased the level of cognition and automation in space networks. However spectrum agility alone cannot ensure reliable communications for space networks, network agility across protocol layers for environmental awareness and autonomous reconfiguration among networked nodes is also needed. Specifically, multi-hop wireless/satellite networks with the Dynamic Radio Spectrum (DSA) require the development of novel spectrum-aware routing and scheduling algorithms. Results from traditional wireless networks cannot be directly applied due to unique characteristics of space networks including large propagation delay, limited storage space, and intermittent and asymmetric links. Accordingly, further investigation is needed to understand the application of cognitive and automation technologies that enable network agility in space networks. IAI will develop a self-learning and adaptive communication system (s-LEAD) for advanced space networks. The s-LEAD architecture will allow space communication systems to adaptively reconfigure network elements based upon network conditions, policies, and mission requirements. s-LEAD builds on a cross-layer optimization framework to create an adaptive, self-optimizing CR network capable of responding to environmental changes through joint control of spectrum management, physical-layer cooperation, and traditional networking functionalities. The key innovation of s-LEAD is developing an adaptive decision making system with DSA capability for hybrid satellite and ground networks with diverse traffic characteristics and quality-of-service requirements. IAI will investigate example scenarios from NASA robotic and human missions in low Earth orbit to deep space, operating in a variety of spacecraft.