Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$, where each path costs at most $K$ responses or episodes.
arXiv:2606. 29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review.
By Mengdie Flora Wang, Haochen Xie, Guanghui Wang, Devin Zhang, Jae Oh Woo
Repeated-sampling evaluations increasingly extrapolate pass@k far beyond the number n of samples collected per problem. We show that, in the pooled/random-task conditional-Binomial model, fixed-n succ...
arXiv:2609.09245v1 Announce Type: new
Abstract: Repeated-sampling evaluations increasingly extrapolate pass@k far beyond the number n of samples collected per problem. We show that, in the pooled/ran...
By Pranav Singh, Prashant Singh
arXiv:2606.00920v2 Announce Type: replace-cross
Abstract: A benchmark score is a measurement whose uncertainty has two sources: an aleatoric component from stochastic decoding and an epistemic compon...
By Yongxi Zhou, Lai Yun Choi, Jiaxi Wen, Wenbo Ye, Junwei Yao
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
By Pixel Nomand, Elena Voss, Marcus Hale, Sofia Reyes