Sungchul Kim | Xunyi's Academic Websitehttps://jiangxunyi.github.io/authors/sungchul-kim/Sungchul KimHugo Blox Builder (https://hugoblox.com)en-usMon, 20 Jul 2026 00:00:00 +0000https://jiangxunyi.github.io/media/icon_hu12864870738162112581.pngSungchul Kimhttps://jiangxunyi.github.io/authors/sungchul-kim/Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steeringhttps://jiangxunyi.github.io/publication/selfloops/Mon, 20 Jul 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/selfloops/<p>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.</p>