Magistral
Paper
•
2506.10910
•
Published
•
63
Reasoning
-
-
Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
Paper • 2506.15882 • Published • 2 -
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization
Paper • 2507.14683 • Published • 126 -
The Invisible Leash: Why RLVR May Not Escape Its Origin
Paper • 2507.14843 • Published • 84 -
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Paper • 2507.15778 • Published • 19 -
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Paper • 2507.19457 • Published • 24