Tag
This paper investigates the reliability of LLM judges for complex professional tasks using patent drafting as a testbed, finding that judge-guided revision improves quality but exhibits metric-dependent agreement with human expert evaluation.
Early access to new Xiaomi MiMo-X-Pro-Preview and MiMo-X-Flash-Preview AI models for professional workflows, focusing on complex reasoning and multi-agent collaboration.
GMKtec announces the launch of a new AI-powered computing platform featuring the AMD Ryzen AI Max+ PRO 495 processor at IFA Berlin 2026, targeting advanced AI applications and professional workflows.
DeskCraft is a new benchmark for evaluating desktop GUI agents on long-horizon professional creative workflows, incorporating human-in-the-loop collaboration protocols. It tests agents on tasks requiring over 50 steps across design, video, audio, and 3D software.