这篇论文提出了FPRM，用固定点收敛让循环推理深度自适应任务难度，在Sudoku和ARC-AGI上效果不错，适合关注推理架构的人。
循环架构通过循环利用层数为组合推理任务提供逐步推理的归纳偏置。随着循环深度增加，信号传播问题加剧，影响模型性能。本文提出FPRM，一种基于Transformer的固定点推理模型，采用预归一化层和残差缩放解决信号传播，并以固定点收敛作为端到端停止机制。FPRM在Sudoku、Maze、状态跟踪和ARC-AGI基准上验证了有效性。
Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
Looped architectures provide an inductive bias toward learning step-by-step procedures for tasks that require compositional reasoning. The number of effective layers reached by looping determines the quality of the solution these models find. Like deep architectures, looped architectures are prone to a signal propagation problem induced by depth as the halting decision is postponed. In this paper, we address this signal propagation issue using pre-norm layers and residual scaling. Building on these architectural modifications, we propose FPRM, a Transformer-based Fixed-Point Reasoning Model that uses fixed-point convergence as an end-to-end halting mechanism in a looped architecture. We show that fixed-point halting allows FPRM to adapt its compute to task difficulty. FPRM is effective on common reasoning benchmarks, namely Sudoku, Maze, state-tracking, and ARC-AGI.