LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published Jun 10 • 79
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch Paper • 2606.10728 • Published Jun 9 • 36
ClawGym: A Scalable Framework for Building Effective Claw Agents Paper • 2604.26904 • Published Apr 29 • 54
Toward Autonomous Long-Horizon Engineering for ML Research Paper • 2604.13018 • Published Apr 14 • 34
SWE Agent Series Collection Models trained by SWE-Master and SWE-World, including both policy models and verifiers. • 13 items • Updated Mar 23 • 4
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Paper • 2603.03194 • Published Mar 3 • 57
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training Paper • 2602.03411 • Published Feb 3 • 39
SWE-World: Building Software Engineering Agents in Docker-Free Environments Paper • 2602.03419 • Published Feb 3 • 41
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models Paper • 2503.21380 • Published Mar 27, 2025 • 38
YuLan-Mini Resources Collection Pre-Training & post-training resources for YuLan-Mini • 29 items • Updated May 7, 2025 • 3