OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models Paper • 2607.28609 • Published 20 days ago • 72
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory Paper • 2607.24368 • Published 23 days ago • 33
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation Paper • 2605.25874 • Published May 25 • 106
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification Paper • 2601.15808 • Published Jan 22 • 20
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent Paper • 2601.07779 • Published Jan 12 • 28
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone Paper • 2512.22615 • Published Dec 27, 2025 • 51
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives Paper • 2512.14699 • Published Dec 16, 2025 • 29
Guided Self-Evolving LLMs with Minimal Human Supervision Paper • 2512.02472 • Published Dec 2, 2025 • 55
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows Paper • 2510.24411 • Published Oct 28, 2025 • 73
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows Paper • 2510.24411 • Published Oct 28, 2025 • 73