AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses Paper • 2608.12307 • Published 4 days ago • 108
Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation Paper • 2608.06751 • Published 9 days ago • 27
Stealing Reasoning Traces from Proprietary LLM APIs Paper • 2608.09867 • Published 6 days ago • 101
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition Paper • 2607.25565 • Published 19 days ago • 65
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers Paper • 2607.21594 • Published 24 days ago • 16
VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection Paper • 2505.20289 • Published May 26, 2025 • 11
MAOAM: Unified Object and Material Selection with Vision-Language Models Paper • 2606.04880 • Published Jun 2 • 10
From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing Paper • 2605.15181 • Published May 14 • 12
Exploration and Exploitation Errors Are Measurable for Language Model Agents Paper • 2604.13151 • Published Apr 14 • 25 • 3
Exploration and Exploitation Errors Are Measurable for Language Model Agents Paper • 2604.13151 • Published Apr 14 • 25