Tag
The paper introduces Readout Feedback (RoFB), a test-time intervention that steers latent dynamics in recurrent reasoning models using their own readout probabilities, achieving performance gains on Sudoku and Maze tasks without retraining.
Introduces SPARK, a method that uses length-controlled hidden-state susceptibility to diagnose and steer reasoning states in LLMs, improving accuracy on mathematical reasoning benchmarks such as GSM8K and MATH-500.