Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior
Luyang Zhang, Jialu Wang, Fei Xue +1
Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordinate as agents. Their value depends on the models producing measurably different…
cs.CL2026
Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics
Luyang Zhang, Jingyan Li
Best-of- inference scaling (drawing candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by an amount that varies ac…