Persona Dosing: Calibrated Activation Steering for Graded Trait Control Paper • 2609.36388 • Published 7 days ago • 48
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields Paper • 2606.11042 • Published Jun 9 • 221
Post-Training Leaves Behavioral Shadows on Unrelated Decisions Paper • 2609.29233 • Published 11 days ago • 271
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue Paper • 2609.31948 • Published 10 days ago • 89
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 13 days ago • 162