Tag
This paper studies quantization of recursive reasoning models where weight-tied blocks are reused, finding that per-tensor 4-bit quantization causes catastrophic drift but per-block scaling (e.g., MXInt4) restores accuracy, with deeper architectures being more sensitive.
Introduces the Energy-guided Recursive Model (ERM), which uses Hopfield energies to guide selection among recursive reasoning trajectories, achieving state-of-the-art performance on Sudoku, Pencil Puzzle Bench, and Maze tasks.
A systematic study of compressing recursive reasoning models for edge hardware finds that aggressive quantization destroys global reasoning while preserving local prediction. The paper introduces per-channel calibrated INT4 to recover reasoning ability and provides deployment recipes fitting 8 MB SoC and 4 MB MCU targets.
The paper reveals that latent reasoning in transformer-based reasoning models (TRMs) functions as a policy improvement operator, and proposes an algorithm that enhances learning and inference efficiency by up to 18x.
Introducing RecToM, an inference-time framework that models nested beliefs via recursive perspective construction for Theory of Mind reasoning in LLMs, achieving state-of-the-art performance on multiple benchmarks.
This paper introduces Generative Recursive reAsoning Models (GRAM), a probabilistic framework that extends recursive reasoning models by enabling stochastic latent trajectories, multiple hypotheses, and inference-time scaling through depth and parallel sampling.
This paper proposes an epistemic state graph representation and an order-gap termination criterion for recursive reasoning systems, addressing how to manage evolving reasoning states and when to stop iteration.