EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction Paper • 2609.02783 • Published 24 days ago • 62
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring Paper • 2608.09802 • Published Aug 10 • 84
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published Apr 24 • 158
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 143
DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation Paper • 2511.23127 • Published Nov 28, 2025 • 25