Peer-to-peer search networks are a popular and widely deployed means of
searching massively distributed digital object repositories.
Unfortunately, as such networks grow, they place an increasingly
overwhelming load on some or all of the participating nodes. We examine
how to reduce the load on nodes by allowing them to self-organize into a
relatively efficient network, and then self-tune to make the network even
more efficient. Unlike previously studied architectures, our ``ad hoc,
self-supervising'' networks avoid restrictions on who a node can connect
to or what information can be exchanged. This makes the network topology
quite flexible and tuneable. Our results indicate that ad hoc networks are
more efficient than popular supernode topologies for several important
scenarios.