Persona Dosing: Calibrated Activation Steering for Graded Trait Control Paper • 2609.36388 • Published 7 days ago • 48
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published Aug 18 • 138
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation Paper • 2609.03254 • Published Sep 3 • 6