We investigate the problem of topology aggregation (TA) for scalable, QoS-based routing in ATM networks. TA is the process of summarizing the topological information of a subset of network elements. This summary is flooded throughout the network, and is used by various nodes to determine appropriate routes for connection requests. A key issue in the design of a TA scheme is the appropriate balance between compaction and the corresponding routing performance. The contributions of this paper are twofold. First, we introduce a source-oriented approach to TA, which provides better performance than existing approaches. The intuition behind this approach is that the advertised topology-state information is used by source nodes to determine tentative routes for connection requests. Accordingly, only relevant information to source nodes needs to be advertised. We integrate the source-oriented approach into three new TA schemes that provide different tradeoffs between compaction and accuracy. Second, we extend our source-oriented approach to multi-QoS-based TA. A key issue here is the determination of appropriate values for the multiple QoS parameters that are associated with a logical link. Two new approaches to computing these values are introduced. Extensive simulations are used to evaluate the performance of our proposed schemes.