Author

Gagan Mundada

h-index 4 View on Semantic Scholar

We have 1 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

This work treats each reasoning trace as a sequence of latent states rather than an unstructured texts, and investigates whether inference time interventions can provide fine-grained control over the self-looping reasoning process.

Sheldon Yu, Tong Yu, Xunyi Jiang et al. · arXiv.org · 0 citations