AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Recent large language models achieve strong performance on complex reasoning tasks, where reinforcement learning with Group Relative Policy Optimization (GRPO) has emerged as a leading paradigm for optimizing models on self-generated trajectories. However, the on-policy nature of GRPO bounds the model to the reasoning skills it can already produce, restricting to learn more advanced capabilities. Prior works inject privileged reasoning traces from a stronger teacher policy to guide training, yet these traces are inherently out of distribution with respect to the student policy. We observe that

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T08:51:59.673Z. This is not the publication date.