2 papers
cs.LG2026
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20
We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabili…
cs.LG2026
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
Lena Krieger, Xuan Zhao, Zhuo Cao +3
Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback. A key diffi…