通过语义和事件记忆学习：一种反思式智能体适应方法
Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation
AI总结：
本文提出一种基于记忆增强的框架，利用预训练大语言模型生成的批判性反馈，通过语义和事件记忆提升智能体适应能力，实验证明其在多个任务中有效。
摘要：
我们研究了基于预训练大语言模型（LLMs）的智能体如何从带标签的示例中学习目标分类函数，而无需参数更新。传统方法如微调通常成本高、不灵活且不透明，我们提出了一种记忆增强框架，利用LLM生成的基于带标签数据的批判性反馈。该框架使用事件记忆存储实例级批判，捕捉特定的过往经验，并利用语义记忆将其提炼为可重用的任务级指导。在多种任务和模型上，我们最佳的自我批判策略（利用两种记忆类型）在零样本基线下平均提升8.1个百分点，在仅依赖标签的RAG基线下提升4.6个百分点。然而，改进在不同模型和领域中差异显著。为解释这种差异，我们引入了“可说服性”——一种衡量模型对上下文提供外部推理的接受程度的新指标。我们使用可说服性来阐明记忆增强何时和为何成功或失败。除了准确率提升外，我们发现预计算的批判显著减少了推理模型推理时间的计算量，平均减少31.95%的思考令牌，通过替代模型原本独立执行的推理。我们的发现突显了在何种条件下基于记忆的反思学习可以作为轻量、可解释和高效的策略，以提高LLM的适应性。
英文摘要：
We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly, inflexible, and opaque, we propose a memory-augmented framework that leverages LLM-generated critiques grounded in labeled data. Our framework uses episodic memory to store instance-level critiques - capturing specific past experiences - and semantic memory to distill these into reusable, task-level guidance. Across a diverse set of tasks and models, our best performing self-critique strategy (utilizing both memory types) yields an average improvement of 8.1 percentage points over the zero shot baseline, and 4.6pp over a RAG-based baseline that relies only on labels. However, improvements vary substantially across models and domains. To explain this variation, we introduce suggestibility - a novel metric capturing how receptive a model is to external reasoning provided in context. We use suggestibility to illuminate when and why memory augmentation succeeds or falls short. Beyond accuracy gains, we find pre-computed critiques substantially reduce inference-time computation for reasoning models, cutting thinking tokens by an average of 31.95% across all datasets by substituting for reasoning that the model would otherwise perform independently. Our findings highlight the conditions under which memory-driven, reflective learning can serve as a lightweight, interpretable, and efficient strategy for improving LLM adaptability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
