Eduardo-27B is a math tutor trained with multi-turn reinforcement learning. It was fine-tuned from Qwen/Qwen3.8-27B to teach a student how to solve a problem rather than solve it for them. It was introduced in The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning. 📄 Paper (arXiv:2610.06446) · 💻 Code · 📊 Near-transfer dataset Eduardo is trained in a simulated classroom: it holds full multi-turn dialogs (up to 22 turns) with a frozen student (Llama-3.1-8B-Instruct) on math problems from Big-Math. The student gets no persona prompt, so its errors are its own, not role-play. No human annotations are used. The reward is the student’s normalized learning gain on a masked near-transfer post-test. After the dialog, the student attempts an unseen variant of the tutored problem. During this test the student sees only its own turns, because every tutor turn is replaced by (hidden). So the reward can rise only through what the student wrote in its own turns, not through what the tutor said. Two binary gates, judged by Qwen3.6-27B, guard the reward: — Factual correctness: everything the tutor states must be mathematically correct. — No solution handover: the tutor…
Модальности:
Генерация текста
Области применения:
Математика Диалог / чат
Задача: Генерация текста
Автор: eth-nlped
Теги: qwen3_5, image-text-to-text, education, tutoring, math, pedagogy, reinforcement-learning, multi-turn-rl
Лайков: 3 | Загрузок: 416
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
