Universe of Thoughts: Enabling Creative Reasoning with Large Language Models

ICLR 2026 Conference Submission19253 Authors

Keywords: LLM, Universe of Thoughts, Creative Reasoning

TL;DR: We propose the "Universe of Thoughts," a novel framework that enables Large Language Models to generate more creative solutions to complex problems by drawing on a broad range of concepts, outperforming current state-of-the-art reasoning methods.

Abstract: Reasoning based on Large Language Models (LLMs) has garnered increasing attention due to outstanding performance of these models in mathematical and complex logical tasks. Beginning with the Chain-of-Thought (CoT) prompting technique, numerous reasoning methods have emerged that decompose problems into smaller, sequential steps (or thoughts). However, existing reasoning models focus on conventional problem-solving and do not necessarily generate creative solutions by ``creative reasoning''. In domains where the solution space is expansive and conventional solutions are suboptimal, such as drug discovery or business strategization, creative reasoning to discover innovative solutions is crucial. To address this gap, first we introduce a computational framework for creative reasoning inspired by established cognitive science principles. With this framework, we propose three core creative reasoning paradigms, namely, combinational, exploratory, and transformative reasoning, where each offers specific directions for systematic exploration of the universe of thoughts to generate creative solutions. Next, to materialize this framework using LLMs, we introduce the Universe of Thoughts (or UoT, for short), a novel set of methods to implement the aforementioned three creative processes. Finally, we introduce three novel tasks that necessitate creative problem-solving, along with an evaluation benchmark to assess creativity from three orthogonal perspectives: feasibility as constraint, and utility and novelty as metrics. With a comparative analysis against the state-of-the-art (SOTA) reasoning techniques as well as representative commercial models with reasoning capability, we show that UoT demonstrates superior performance in creative reasoning. This work introduces a new perspective on how LLMs can become autonomously creative, advancing the field to address problems that require more innovative solutions.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 19253