Sampling - Tag - lilfry's libraryhttps://lilfry09.github.io/en/tags/sampling/Sampling - Tag - lilfry's libraryHugo -- gohugo.ioenlilfry@sjtu.edu.cn (lilfry)lilfry@sjtu.edu.cn (lilfry)All rights reserved.Tue, 07 Apr 2026 20:55:00 +0800Read "Reasoning with Sampling": RL does not make the model smarter, it just redistributes reasoning capabilitieshttps://lilfry09.github.io/en/ai/reasoning-with-sampling-rl-redistribution/Tue, 07 Apr 2026 20:55:00 +0800fryhttps://lilfry09.github.io/en/ai/reasoning-with-sampling-rl-redistribution/The really dangerous thing about this paper is not that it proposes a new sampler, but that it asks a deeper interpretive question:

**The progress of reasoning model, is it that the model has learned new capabilities, or have we finally learned how to sample from old capabilities? **

If this question were asked correctly, much of the narrative about RL for reasoning would have to be rewritten.

]]>