Preprints|Research ArticleNot peer reviewedMining Failure Modes from Agent Trajectories at ScaleAisha Rahman, Lena HartwellVersion 1 · 21 October 2026 · 10.xxxx/ctm.pp.2026.0007Abstract PDF 2,065 6901 cited
Proceedings|Full paperBest paperRetry Budgets for Tool-Using Agents: When Is Trying Again Worth It?Aisha Rahman, Lena HartwellRTUA 2026 · pp. 1–9 · 3 July 2026 · 10.xxxx/ctm.pr.2026.0001Abstract PDF 1,420 5602 cited
Proceedings|Extended abstractPerturbation Suites for Measuring Agent Reliability: Lessons from Three DeploymentsHana Kovács, Aisha RahmanRTUA 2026 · pp. 31–33 · 3 July 2026 · 10.xxxx/ctm.pr.2026.0005Abstract PDF 440 1500 cited