TREK: Distill to Explore, Reinforce to Refine
Teaching AI to solve hard problems by learning from smarter teachers first
A new method called TREK helps AI models solve difficult math and reasoning problems by first learning verified solutions from a stronger teacher, then refining its own approach. On challenging math competitions, the method improved Qwen3-8B's score on AIME 2025 from 36.9 to 40.3, and lifted performance on agent-based tasks like virtual world navigation from 75.8 to 82.8 percent success.
AI systems currently struggle when faced with hard problems outside their normal experience. TREK fixes this by letting models learn from external teachers—whether a more powerful AI, a human-created solution, or the model itself with extra context—then polish those solutions through standard training. This means better reasoning AI without requiring expensive human feedback or labeled training data, directly improving performance on math competitions and complex real-world tasks.