AI Model Achieves Gold-Medal Performance on International Mathematics Olympiad Problems
Researchers have developed MaxProof, an AI system that solves competition-level mathematical proofs at the level of human gold medalists on the IMO 2025 and USAMO 2026 benchmarks. The system uses a generative-verifier approach combined with reinforcement learning and population-level test-time scaling to generate, verify, and refine mathematical proofs. This represents a significant milestone in AI's ability to tackle complex mathematical reasoning tasks that require rigorous proof construction.
MaxProof is a test-time scaling framework built on the MiniMax-M3 series that addresses competition-level mathematical proof problems. The system trains three core capabilities—proof generation, proof verification, and critique-conditioned proof repair—using a defense-in-depth generative verifier designed to minimize false positives. At test time, the framework treats the M3 model as a generator, verifier, refiner, and ranker, searching across a population of candidate proofs and selecting the final answer through tournament selection. The results demonstrate that with this approach, the M3 model achieves 35/42 on IMO 2025 and 36/42 on USAMO 2026, both exceeding the human gold-medal threshold. This work represents progress in applying reinforcement learning and population-based search strategies to mathematical reasoning.
What's missing
The paper does not discuss potential limitations of the approach, such as computational cost of test-time scaling, generalization to novel proof types not seen during training, or comparison with other recent mathematical reasoning systems. The study's own caveats regarding the scope of problems tested and applicability beyond competition mathematics are not detailed in the abstract.
What different sources said
- arXiv cs.AICenter
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Related
Topology-Aware Thermodynamics Improves DNA Probe Specificity Design
Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.
Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors
Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.
Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance
Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.