If this worked then a team of five fable models should crush al of its benchmarks, no?
I kid, but also not. If the smart model already has a smart plan, odds aren’t great more smart models are going to create an even smarter plan. Not entirely true because that is the goal of parallelizing discovery attempts, but the point is there is more room to gain benefit from adding additional inference-time compute with a smaller model than one that already had a ton of compute to begin with.