---
title: "LLM能否从经验抽象中获益？——自我提醒机制研究"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.20372v1"
permalink: "https://feed.astralor.com/items/itm_e95f8e8fac39d7bc07921004"
published: "2026-07-22T17:02:34.000Z"
score: 76
channel: "ai"
tags: ["大语言模型","强化学习","推理时检索","数学推理","经验抽象"]
---

# LLM能否从经验抽象中获益？——自我提醒机制研究

## AI 点评

> 这篇论文让我眼前一亮，因为它把人类认知中‘经验复盘’的概念巧妙地迁移到了大模型上。相比那些堆算力或数据的方法，这种‘自我提醒’的思路要优雅得多。尤其适合那些关注LLM推理优化、Agent自我迭代的研究者。当然，目前只看到数学和逻辑任务的效果，扩展到常识或开放域会更有说服力。

## 速览

该论文探索LLM能否像人类一样从解题经验中提取可重用抽象策略（如策略和警示性提醒），并构建可检索库。实验在MATH训练集上通过教师或LLM自身提取抽象，支持推理时检索和基于强化学习的提示增强两种模式。结果显示，经验抽象显著提升数学和逻辑推理基准性能，自提取抽象效果与教师提取相当，且框架可跨数据集和模型迁移，表明LLM具备类似人类经验蒸馏的能力。

## 关键点

- 从LLM解题痕迹中提取自然语言抽象策略（如提醒和策略）并构建可检索库
- 支持两种使用模式：推理时检索和强化学习提示增强
- 在数学和逻辑推理基准上显著提升性能，自提取与教师提取效果相当
- 框架可迁移到其他数据集和模型，展示泛化能力

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e95f8e8fac39d7bc07921004