StopLoss aborts likely-failing coding-agent runs early
On SWE-bench Verified it cut cost per retained solve by 4.5 percent while keeping 99 percent of successful runs.
Stories per day · 30 days
2 RSS
Relatedbenchmarks1coding-agents1decision-theory1deep-learning1inference-cost1monitors1observational-equivalence1quantile-loss1regression1resource-allocation1risk-estimation1swe-bench1tabular-learning1
3 stories, newest first · one card per story
Stories tagged #early-stopping
Paper finds waiting identifies exactly two risk moments per period
A length-τ observation prefix identifies moments through order 2τ−1, but not necessarily allocation welfare.
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
Tabular deep regression study finds quantile loss beats tuned MSE, but global early stopping still compromises noisy regions.