将检索策略选择封装为可复用的智能体技能，提升多任务检索效果。
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
- 设计可插拔的检索编排层，根据场景动态选策略。
- 在三个数据集上nDCG@10达0.8924，优于固定检索器。
- 适合需要灵活检索的智能体系统开发者使用。
检索增强生成系统通常假设单一固定检索流程适用于所有异构任务，但事实类问答、多跳推理和科学验证等任务对检索的需求不同。本文提出Experience-RAG Skill，一种位于智能体与检索器池之间的面向智能体的可插拔检索编排层。该技能分析当前场景，查询经验记忆，选择合适检索策略，并向智能体返回结构化证据。在固定候选池下，Experience-RAG Skill在BeIR/nq、BeIR/hotpotqa和BeIR/scifact三个数据集上的nDCG@10综合达到0.8924，优于固定单检索器基线，且与自适应路由型方法相当。结果表明，检索策略选择可有效封装为可复用的智能体技能，而非硬编码于上层流程中。
原文摘要 · Abstract (English)
Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval preferences. We present Experience-RAG Skill, an agent-oriented pluggable retrieval orchestration layer positioned between the agent and the retriever pool. The proposed skill analyzes the current scene, consults an experience memory, selects an appropriate retrieval strategy, and returns structured evidence to the agent. Under a fixed candidate pool, Experience-RAG Skill achieves an overall nDCG@10 of 0.8924 on BeIR/nq, BeIR/hotpotqa, and BeIR/scifact, outperforming fixed single-retriever baselines and remaining competitive with Adaptive-RAG-style routing. The results suggest that retrieval strategy selection can be productively encapsulated as a reusable agent skill rather than being hard-coded in the upper workflow.
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。