用过往经验增强大模型智能，让其决策更可靠、有记忆、可解释。
Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integration
- 引入案例推理机制，让大模型调用历史经验解决问题。
- 构建数学模型优化案例检索、适应与学习流程，提升推理效率。
- 适合需要可解释性、长期记忆的智能体应用，如医疗、金融决策。
由大语言模型（LLMs）驱动的智能体在多种任务中展现出强大能力，但在需要特定结构化知识、灵活性或可问责决策的任务中仍存在局限。尽管智能体能感知环境、推理规划并执行动作，却常出现幻觉、缺乏跨交互上下文记忆等问题。本文探讨将案例推理（Case-Based Reasoning, CBR）融入LLM智能体框架的可行性，通过调用过往经验来解决新问题，从而显式利用知识以提升效果。系统回顾了增强型智能体的理论基础，识别关键架构组件，并构建了案例检索、适应与学习过程的数学模型。对比链式思考（Chain-of-Thought）与标准检索增强生成（Retrieval-Augmented Generation）等方法，分析其相对优势。进一步探索通过目标驱动自治机制，融合自省、内省与好奇心等认知维度，以增强智能体能力。本研究推动神经符号混合系统发展，提出CBR是提升自主LLM智能体推理与认知能力的有效路径。
原文摘要 · Abstract (English)
Agents powered by Large Language Models (LLMs) have recently demonstrated impressive capabilities in various tasks. Still, they face limitations in tasks requiring specific, structured knowledge, flexibility, or accountable decision-making. While agents are capable of perceiving their environments, forming inferences, planning, and executing actions towards goals, they often face issues such as hallucinations and lack of contextual memory across interactions. This paper explores how Case-Based Reasoning (CBR), a strategy that solves new problems by referencing past experiences, can be integrated into LLM agent frameworks. This integration allows LLMs to leverage explicit knowledge, enhancing their effectiveness. We systematically review the theoretical foundations of these enhanced agents, identify critical framework components, and formulate a mathematical model for the CBR processes of case retrieval, adaptation, and learning. We also evaluate CBR-enhanced agents against other methods like Chain-of-Thought reasoning and standard Retrieval-Augmented Generation, analyzing their relative strengths. Moreover, we explore how leveraging CBR's cognitive dimensions (including self-reflection, introspection, and curiosity) via goal-driven autonomy mechanisms can further enhance the LLM agent capabilities. Contributing to the ongoing research on neuro-symbolic hybrid systems, this work posits CBR as a viable technique for enhancing the reasoning skills and cognitive aspects of autonomous LLM agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。