Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 17 days ago • 43
Immersion in the GitHub Universe: Scaling Coding Agents to Mastery Paper • 2602.09892 • Published Feb 10 • 6
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Paper • 2603.03194 • Published Mar 3 • 57
Toward Autonomous Long-Horizon Engineering for ML Research Paper • 2604.13018 • Published Apr 14 • 34
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch Paper • 2606.10728 • Published Jun 9 • 37
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks Paper • 2608.06352 • Published Aug 6 • 24