面向经验的可插拔经验型RAG技能：用于经验驱动的检索策略编排
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
AI总结：
本文提出经验型RAG技能，通过分析场景和经验记忆选择合适检索策略，提升多任务检索效果，实测在多个数据集上优于固定检索基线。
摘要：
检索增强生成系统通常假设固定检索流程适用于异构任务，但事实性问答、多跳推理和科学验证显示不同的检索偏好。我们提出了经验型RAG技能，作为代理与检索池之间的可插拔检索编排层。该技能分析当前场景，咨询经验记忆，选择合适检索策略，并将结构化证据返回给代理。在固定候选池下，经验型RAG技能在BeIR/nq、BeIR/hotpotqa和BeIR/scifact数据集上实现了整体nDCG@10为0.8924，优于固定单检索器基线并在与Adaptive-RAG风格路由竞争中保持竞争力。结果表明，检索策略选择可以作为可重用的代理技能封装，而非硬编码在上层工作流中。
英文摘要：
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.
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。
