SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations Paper • 2611.20218 • Published 6 days ago • 52
SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published Oct 19 • 98
Can a Lightweight Automated AI Pipeline Solve Research-Level Mathematical Problems? Paper • 2602.13695 • Published Feb 14
Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates Paper • 2412.01564 • Published Dec 2, 2024
FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards Paper • 2604.26733 • Published May 15 • 1
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published Sep 11 • 97
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks Paper • 2609.18805 • Published Sep 16 • 40
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Paper • 2609.19134 • Published Sep 16 • 72
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published Sep 11 • 97 • 8