I think the point goes towards the idea that the rewards should be related to the risk.

Commercializing IP - which is not a product yet - is non-trivial, could take years to productize, and then longer to penetrate (or create) a market. In short, it's a long, painful, and often expensive process that often fails anyway. If there was a way to provide a license agreement that was more favorable to product/market validation, that could change the economics.

Unfortunately, I've only participated in licensing once, so I don't have an alternative model to suggest.