[论文解读] Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
本文提出 InteRecAgent,这是一个紧凑的基于 LLM 的框架,利用大语言模型作为大脑,传统推荐工具作为引擎,以实现具有记忆、规划和反思的交互式对话式推荐。
Recommender models excel at providing domain-specific item recommendations by leveraging extensive user behavior data. Despite their ability to act as lightweight domain experts, they struggle to perform versatile tasks such as providing explanations and engaging in conversations. On the other hand, large language models (LLMs) represent a significant step towards artificial general intelligence, showcasing remarkable capabilities in instruction comprehension, commonsense reasoning, and human interaction. However, LLMs lack the knowledge of domain-specific item catalogs and behavioral patterns, particularly in areas that diverge from general world knowledge, such as online e-commerce. Finetuning LLMs for each domain is neither economic nor efficient. In this paper, we bridge the gap between recommender models and LLMs, combining their respective strengths to create a versatile and interactive recommender system. We introduce an efficient framework called extbf{InteRecAgent}, which employs LLMs as the brain and recommender models as tools. We first outline a minimal set of essential tools required to transform LLMs into InteRecAgent. We then propose an efficient workflow within InteRecAgent for task execution, incorporating key components such as memory components, dynamic demonstration-augmented task planning, and reflection. InteRecAgent enables traditional recommender systems, such as those ID-based matrix factorization models, to become interactive systems with a natural language interface through the integration of LLMs. Experimental results on several public datasets show that InteRecAgent achieves satisfying performance as a conversational recommender system, outperforming general-purpose LLMs. The source code of InteRecAgent is released at https://aka.ms/recagent.
研究动机与目标
- 弥合 LLM 的通用能力与领域特定推荐需求之间的差距。
- 通过自然语言界面使推荐系统具互动性。
- 提出记忆、规划与反思模块,以提升工具使用效果和鲁棒性。
- 使小型语言模型能够在推荐任务中模拟“大脑”的功能。
- 在公开数据集上证明有效性,并发布适用于小模型的 RecLlama。
提出的方法
- 为 LLM 驱动的互动式推荐定义一个最小工具集(信息查询、物品检索、排序)。
- 引入 Candidate Bus 内存,在工具之间流式传递候选项。
- 维护长短期用户画像,在跨对话中个性化推荐。
- 采用以计划优先的执行并结合动态演示,以减少提示和 API 调用。
- 融入 actor-critic 反思机制,在工具使用过程中识别并纠正错误。
- 通过在 imitation 数据集上对 GPT-4 生成的工具规划数据进行微调,训练 RecLlama (7B)。
实验结果
研究问题
- RQ1如何将 LLM 与传统推荐工具集成,以实现交互式、自然语言的推荐?
- RQ2记忆、规划和反思模块是否能提高工具使用准确性和最终推荐效果?
- RQ3在使用 GPT-4 生成的数据进行训练时,小型语言模型是否能达到与大模型相竞争的推荐代理“大脑”性能?
主要发现
- InteRecAgent 在多个公开数据集上实现了具有竞争力的对话式推荐性能。
- 以计划优先的执行策略相较逐步方法,降低了 API 调用和延迟。
- 动态演示通过选择与当前用户意图最相似的示例来提升规划质量。
- 记忆模块(Candidate Bus 与用户画像)使长期对话中的通信与个性化具有可扩展性。
- RecLlama,一个在 GPT-4 派生数据上微调的 7B 模型,在充当推荐代理时胜过一些更大模型。
- 实验在世界知识覆盖较少的领域(如 Beauty 数据集)显示出显著优势。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。