Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Learning with a Single Rollout via Pass@k Policy Optimization
Fengdi Che, Yang Liu, Lei Yu +4
Group Relative Policy Optimization (GRPO) typically requires multiple rollouts per prompt to estimate relative credit, incurring substantial sampling cost and exacerbating training…
cs.CL2026
Universal computation is intrinsic to language model decoding
Alex Lewandowski, Marlos C. Machado, Dale Schuurmans
Language models now provide an interface to express and often solve general problems in natural language, yet their ultimate computational capabilities remain a major topic of scie…