发表机构
Auton Lab, Carnegie Mellon University（卡内基梅隆大学自动实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型能否从经验抽象中受益，通过从其在MATH训练集的痕迹提取抽象存入可检索库，探索推理时检索和强化学习两种使用模式，发现能提高模型在数学和逻辑推理基准上的性能，且框架可转移。
AI 中文摘要
人类将经验提炼为可复用的抽象，如策略和警示提醒，并应用它们逐步更有效地解决问题。我们研究大语言模型（LLMs）是否能同样从这种经验抽象中受益。从LLMs在MATH训练集上的解决方案痕迹中，一个更强的教师模型或LLMs自身将自然语言抽象提取到一个可检索库中。我们探索两种使用模式：（1）推理时检索和（2）使用抽象增强训练提示的强化学习（RL）。经验抽象提高了LLMs在数学和逻辑推理基准上的性能。自我提取的抽象与教师提取的抽象相匹配，且我们的抽象使用框架可转移到其他数据集和模型。这些发现表明LLMs能像人类利用提炼的经验一样提取和应用经验抽象。
英文摘要
Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effectively. We study whether Large Language Models (LLMs) can similarly benefit from such experiential abstractions. From LLMs' solution traces on the MATH training set, a stronger teacher or the LLMs themselves extract natural-language abstractions into a retrievable library. We explore two usage modes: (1) inference-time retrieval and (2) reinforcement learning (RL) with abstraction-augmented training prompts. Experiential abstractions improve LLM performance on mathematical and logical reasoning benchmarks. Self-extracted abstractions match teacher-extracted ones, and our abstraction usage framework can transfer to other datasets and models. These findings suggest LLMs can extract and apply experiential abstractions much as humans leverage distilled experience.
Journal refEMNLP 2026 Findings
