Recent Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence and are a significant step towards human-like artificial intelligence (AI). Yet the performance of LLMs at reasoning tasks have been subpar and the reasoning capability of LLMs is a matter of significant debate. While it has been shown that the choice of the prompting technique to the LLM can alter its performance on a multitude of tasks, including reasoning, the best performing techniques require human-made prompts with the knowledge of the tasks at hand. We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method, where reasons are sampled from an LLM pipeline and mapped into a Quadratic Unconstrained Binary Optimization (QUBO) problem. The framework investigates whether QUBO solutions can be profitably used to select a useful subset of the reasons to construct a Chain-of-Thought style prompt. We explore the acceleration of CR with specialized solvers. We also investigate the performance of simpler zero-shot strategies such as linear majority rule or random selection of reasons. Our preliminary study indicates that coupling a combinatorial solver to generative AI pipelines is an interesting avenue for AI reasoning and elucidates design principles for future CR methods.

最近的大型语言模型（LLMs）在需要人类智能的任务上展示了令人瞩目的能力，是走向人类智能的重要一步。然而，LLMs在推理任务上的表现相对较差，其推理能力成为一个重大争议。我们引入了一种称为组合推理（CR）的全自动提示方法的框架，其中理由是从LLM管道中采样并映射到一个二次无约束二进制优化（QUBO）问题中。该框架探索了QUBO解决方案是否可以有利地用于选择一个有用的理由子集来构建一种“思维链”的提示。我们研究了使用专门求解器加速CR的方法。我们还调查了简单的零样本策略，如线性多数规则或随机选择的理由。我们的初步研究表明，将组合求解器与生成型人工智能管道相结合是人工智能推理的有趣途径，并阐明了未来CR方法的设计原则。

组合推理：通过组合优化在生成型人工智能流程中选择原因