Xunyi's Academic Website
Xunyi's Academic Website
Home
News
Posts
Publications
Projects
Contact
Light
Dark
Automatic
Article
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
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.
Sheldon Yu
,
Tong Yu
,
Xunyi Jiang
,
Rohan Surana
,
Gagan Mundada
,
Sungchul Kim
,
Lina Yao
,
Julian McAuley
,
Junda Wu
PDF
RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
RRPO extends group-relative reinforcement learning to tasks without a direct correctness verifier. It compares candidate rollouts against positive and negative reference sets to construct training advantages for reasoning and open-ended generation.
Yuxin Xiong
,
Xunyi Jiang
,
Rohan Surana
,
Xintong Li
,
Sheldon Yu
,
Nikki Lijing Kuang
,
Ryan A. Rossi
,
Jingbo Shang
,
Tong Yu
,
Julian McAuley
,
Junda Wu
PDF
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Skill-R1 trains a small generator to improve reusable natural-language procedures while keeping the task model fixed. Feedback from successive rollouts guides skill revisions, enabling adaptation with both open and closed models.
Yash Vishe
,
Rohan Surana
,
Xunyi Jiang
,
Zihan Huang
,
Xintong Li
,
Nikki Lijing Kuang
,
Tong Yu
,
Ryan A. Rossi
,
Jingbo Shang
,
Julian McAuley
,
Junda Wu
PDF
Cite
×