AgentProofBench: Benchmarking Reusable Verifiers for Web Agents Paper • 2610.34634 • Published 4 days ago • 14
Editing Images into Reusable Layers via Compositional Edit-Prior Distillation Paper • 2610.24738 • Published 12 days ago • 196
MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion Paper • 2610.25404 • Published 11 days ago • 48
Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams Paper • 2610.27227 • Published 10 days ago • 22
MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing Paper • 2610.23751 • Published 13 days ago • 35
AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published 20 days ago • 93