Generation-adjudication allocation is established as a distinct design axis for reasoning under strict per-instance caps under hard per-instance caps for LLM reasoning.
Yu-Peng Chang, Ya-Han Li, Chen-Lu Guo et al.· 0 citations
An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalization cue. On 100 fresh, independently audited GSM8K test questions per model, it improves delivered endpoint accuracy over first-box stopping by 8.0 p...
Yu-Peng Chang, Lin-Yuan Gao, Zhiyuan Li et al.· 0 citations
Fixed-budget adaptation from heterogeneous data sources requires deciding not only how much data to use, but how much exposure each source receives. Size-proportional rules can crowd out small sources, whereas difficulty-only rules can chase noisy estimates or allocate residual budget to nearly saturated pools. We intr...
Reinforcement learning with verifiable rewards (RLVR) has become a prominent approach for improving language-model performance on reasoning tasks using automatically checked answers. Yet convention-matched evaluation cannot reveal whether reinforcing one reporting convention reduces adherence to a different request tha...
Together, these results show that benefiting from more validation data, outperforming NLL selection, and outperforming the final checkpoint are distinct empirical claims that require separate evidence.