思想宇宙：通过大语言模型实现创造性推理
Universe of Thoughts: A Computational Framework for Creative Reasoning in Large Language Models
AI总结：
通过引入思想宇宙框架，UoT提出了三种创造性推理范式，以提升大语言模型在复杂问题中的创造性解决能力。
摘要：
基于大语言模型（LLMs）的推理能力因在数学和复杂逻辑任务中的出色表现而受到越来越多的关注。从链式思考（CoT）提示技术开始，许多推理方法涌现出来，将问题分解为更小的、连续的步骤（或想法）。然而，现有的推理模型专注于传统问题解决，并不必然通过“创造性推理”生成创新性解决方案。在解决方案空间广阔且传统解决方案不理想的领域，如药物发现或商业战略制定，进行创造性推理以发现创新解决方案至关重要。为解决这一差距，我们首先引入了一种受已确立认知科学原理启发的创造性推理计算框架。借助这一框架，我们提出了三种核心的创造性推理范式，即组合性、探索性和转化性推理，每种都为系统探索思想宇宙提供了特定方向，以生成创造性解决方案。接下来，为了利用LLMs实现这一框架，我们引入了“思想宇宙”（或“UoT”，简称），一种新的方法集，用于实现上述三种创造性过程。最后，我们介绍了需要创造性问题解决的三种新任务，以及一个评估基准，从三个正交的视角评估创造力：可行性作为约束，以及实用性和新颖性作为指标。通过与最先进的（SOTA）推理技术以及具有推理能力的代表性商业模型的比较分析，我们展示了UoT在创造性推理方面表现出色。
英文摘要：
Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively underexplored. Inspired by cognitive science, we formalize combinational, exploratory, and transformational creativity as executable computational operators over structured problem and solution spaces, specifying how each mode combines, explores, or transforms those spaces. Combinational reasoning transfers ideas across domains to form unfamiliar combinations; exploratory reasoning searches for new solutions within an existing conceptual space; and transformational reasoning modifies the rules or constraints that define that space. This formalization yields distinct algorithmic procedures, which we instantiate in Universe of Thoughts (UoT), an LLM reasoning framework. Existing creativity benchmarks emphasize either open-ended ideation or highly constrained problem solving. We therefore introduce three novel creative-reasoning tasks requiring concrete solutions in low-constraint settings. Across 10 generations per method and task, T-UoT with GPT-4o performs strongest on the low-constraint, high-objective-specificity Bridge and Electricity tasks, while C-UoT shows its strongest relative performance on the low-constraint, lower-objective-specificity Society task. In addition, we evaluate UoT on HypoArena, an independent scientific hypothesis-generation benchmark with 100 tasks across biomedical, machine-learning, and social-science domains. With Qwen3-14B, Exploratory UoT ranks first among seven reasoning methods, achieving a 32.7\% pairwise win rate compared with 25.5\% for the next-best method. Our results suggest distinct performance patterns across task structures: T-UoT is strongest in low-constraint, high-specificity settings, E-UoT in more constrained, high-specificity settings, and C-UoT in low-constraint, lower-specificity settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
