Qwen3-1.7B

The paper introduces TTPO, a method designed to optimize LLM reasoning during test-time training by utilizing asymmetric learning signals from pseudo-labels. It effectively mitigates the risks of noisy majority-vote labels by distilling agreeing rollouts and penalizing disagreeing ones.

The paper introduces TTPO, a method designed to optimize LLM reasoning during test-time training by utilizing asymmetric learning signals from pseudo-labels. It effectively mitigates the risks of noisy majority-vote labels by distilling agreeing rollouts and penalizing disagreeing ones.

This research expands on Anthropic's 'Verbalizable-Workspace' paper by applying J-space measurements to open-source models. It characterizes the internal structure of LLMs as having distinct functional zones and demonstrates that steering influence decays via a power law.