StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments Paper • 2608.24804 • Published Aug 25 • 41
FABRIC: Framework for Agent-Based Realistic Intelligence Creation Paper • 2510.17995 • Published Oct 20, 2025
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding Paper • 2607.10400 • Published Jul 11 • 69
ServiceNow/PrivacyAlign-Nemotron-3-Nano-4B-Annotation-Conditioned-Reward Text Generation • Updated Jun 24 • 35 • 1
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding Paper • 2607.10400 • Published Jul 11 • 69
Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning Paper • 2605.09364 • Published May 10
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing Paper • 2603.29852 • Published Feb 22 • 4
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval Paper • 2511.00903 • Published Nov 2, 2025