LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 5 days ago • 183
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails Paper • 2607.05910 • Published 14 days ago • 38
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published 7 days ago • 106
DAVIAN-Robotics/RoboLab-BananaInBowl-30cm-relrate-k1c0-det-gripbin-260716 Viewer • Updated 5 days ago • 376k • 22 • 1
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR Paper • 2606.25178 • Published 24 days ago • 7
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers Paper • 2607.04033 • Published 17 days ago • 76
How Good Can Linear Models Be for Time-Series Forecasting? Paper • 2606.27282 • Published 26 days ago • 13
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Paper • 2606.18837 • Published Jun 17 • 58
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published Jun 11 • 83
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published Jun 4 • 70