GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement We release the GoT-R1 models across three parameter scales. You can access them here: GoT-R1 is a novel reasoning framework that fundamentally redefines how Large Language Models (LLMs) handle complex problem-solving. Developed jointly by Wuhan University and Shanghai Jiao Tong University, GoT-R1 shifts the paradigm from linear Chain-of-Thought (CoT) to an internalized Graph-of-Thought (GoT). While standard CoT models often fall into the «overthinking» trap—generating redundant narrative filler and suffering from cascading errors—GoT-R1 constructs a high-density structured reasoning graph internally. This structural reinforcement ensures that every reasoning node is an atomic logical primitive, enabling the model to solve complex logic tasks with unprecedented accuracy and minimal token usage. — Developer: MYTH-Lab (Wuhan University & Shanghai Jiao Tong University) — Model Type: Causal Language Model with RLHF (GRPO) — Architecture: Transformer-based (4B, 8B, and 14B variants) — License: Apache 2.0 1. High-Density Reasoning: Decouples pure logic from conversational filler. The model learns to output graph…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: MYTH-Lab
Теги: qwen3, reinforcement-learning, grpo, graph-of-thought, reasoning, rlhf, conversational, en
Лайков: 3 | Загрузок: 52
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
