Recent advances in LLMs have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior works focus on modeling reasoning steps using specific thought structures like chains, trees, or graphs. However, LLM-based reasoning continues to encounter three challenges: 1) Selecting appropriate reasoning structures for various tasks; 2) Exploiting known conditions sufficiently and efficiently to deduce new insights; 3) Considering the impact of historical reasoning experience. To address these challenges, we propose DetermLR, a novel reasoning framework that formulates the reasoning process as a transformational journey from indeterminate premises to determinate ones. This process is marked by the incremental accumulation of determinate premises, making the conclusion progressively closer to clarity. DetermLR includes three essential components: 1) Premise identification: We categorize premises into two distinct types: determinate and indeterminate. This empowers LLMs to customize reasoning structures to match the specific task complexities. 2) Premise prioritization and exploration: We leverage quantitative measurements to assess the relevance of each premise to the target, prioritizing more relevant premises for exploring new insights. 3) Iterative process with reasoning memory: We introduce a reasoning memory module to automate storage and extraction of available premises and reasoning paths, preserving historical reasoning details for more accurate premise prioritization. Comprehensive experimental results show that DetermLR outperforms all baselines on four challenging logical reasoning tasks: LogiQA, ProofWriter, FOLIO, and LogicalDeduction. DetermLR can achieve better reasoning performance while requiring fewer visited states, highlighting its superior efficiency and effectiveness in tackling logical reasoning tasks.

翻译：近年来，大语言模型（LLM）的进展彻底改变了推理任务的格局。为了增强LLM模拟人类推理的能力，先前研究主要关注使用特定思维结构（如链、树或图）对推理步骤进行建模。然而，基于LLM的推理仍面临三大挑战：1）针对不同任务选择合适的推理结构；2）充分高效地利用已知条件推导新见解；3）考虑历史推理经验的影响。为解决这些问题，我们提出DetermLR——一种新颖的推理框架，将推理过程形式化为从不确定性前提向确定性前提的转换旅程。这一过程以确定性前提的逐步累积为标志，使结论逐渐趋近清晰。DetermLR包含三个核心组件：1）前提识别：将前提分为确定性与不确定性两类，使LLM能够定制与任务复杂度匹配的推理结构；2）前提优先级排序与探索：利用定量指标评估各前提与目标的相关性，优先探索更高相关性的前提以获取新见解；3）带推理记忆的迭代过程：引入推理记忆模块自动存储和提取可用前提与推理路径，通过保留历史推理细节实现更精准的前提优先级排序。综合实验结果表明，DetermLR在四项具有挑战性的逻辑推理任务（LogiQA、ProofWriter、FOLIO和LogicalDeduction）上均超越所有基线方法。DetermLR能够在减少访问状态数量的同时获得更优的推理性能，凸显其在处理逻辑推理任务时的卓越效率与有效性。