SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 25 days ago • 99
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Paper • 2609.37686 • Published Sep 29 • 47
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence Paper • 2609.35432 • Published Sep 28 • 32
RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation Paper • 2609.18703 • Published Sep 16 • 50
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 54
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published Jul 18 • 87
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks Paper • 2606.09669 • Published Jun 8 • 50
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models Paper • 2604.04707 • Published Apr 6 • 178
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 249