Preprint
Aug 2026
Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study
It is concluded that workflow design was at least as influential as agent capability in this study and proposes diversified search, budgeted moonshot hypotheses, explicit forks, and regime-aware re-validation as testable directions for future autonomous research.
Aon Safdar, Mohamed Saadeldin
· 1 citation