Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Type
Publication
arXiv preprint, 2026
SOPHIA detects when a model repeats unproductive reasoning states and intervenes through hidden-state steering. The method uses transitions between reasoning states to guide generation, improving answer quality and token efficiency.
Xunyi Jiang
PhD in CS @ 🇺🇸NYU
MS in CS @ 🇺🇸UCSD
BS in DS @ 🇨🇳SUSTech
I am interested in LLM Evaluation, Generative Engine Optimization, Human-AI collaboration, AI for creativity🎻.