Preprint
Aug 2026
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
This work establishes a question-level audit under fixed budgets, temperatures, and answer formats, and asks why reachable answers sometimes fail to appear, and test whether inference-time layer routing can expand reachability.
Yanchao Li, Wanhao Liu, Jiaqing Xie et al.
· 0 citations