FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published 3 days ago • 68
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Paper • 2603.03194 • Published Mar 3 • 57
Thinking with Programming Vision: Towards a Unified View for Thinking with Images Paper • 2512.03746 • Published Dec 3, 2025 • 17