JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published 8 days ago • 93
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent Paper • 2508.05748 • Published Aug 7 • 137
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents Paper • 2510.07172 • Published 27 days ago • 28
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training Paper • 2508.00414 • Published Aug 1 • 91
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis Paper • 2412.19723 • Published Dec 27, 2024 • 87