GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents Paper • 2606.24551 • Published Jun 22 • 28
ABForge Collection Paper-grounded ablation design. Unified ABForge-Qwen3-8B (both tasks, one checkpoint), its ablations, and the data. • 4 items • Updated 7 days ago • 1
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published Jun 3 • 39
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems Paper • 2605.04018 • Published May 5 • 41