GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning

Key points

It inserted the latent states to be optimized between prompt representations and generated-token representations at a selected transformer layer, while freezing the base model's parameters.
Through causal self-attention, reward-weighted gradients from all generated tokens flow directly to earlier latent states without a decoding detour.
Average accuracy across five base models, three reasoning benchmarks, and two answer formats was 64.5%, exceeding the strongest comparison method by 2.4 points and chain-of-thought prompting by 6.6 points.
It reduced accuracy variation across seven learning rates from 1.53 to 0.82, and gradient analysis showed that latent influence concentrates on reasoning connectives, also providing interpretability.
The effect was strongest in early-to-middle layers and disappeared in later layers. Evaluation was limited to three reasoning tasks, so layer selection and generalization to other tasks require verification.

External research summaries. These are not HDATF publications or measured product results.