2 papers
cs.LG2026
Efficient Best-of-N policy evaluation for inference-time alignment
Jonas Schweisthal, Yuxin Wang, Athiya Deviyani +2
Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model. Evaluating BoN policies from logged da…
cs.AI2026
ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models
Sam Siavoshian, Omar Ramadan, Amir K. Saeed +3
Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job completion, quota resets, deadlines…