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.HC2026
RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking
Leyi Li, Chenyu Du, Jiafei Sun +2
Computational thinking (CT) is increasingly promoted as a core literacy, yet learners and teachers face challenges in connecting abstract program logic to meaningful outcomes. We d…