# An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

Source: [An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration](<https://www.sota2.com/research/paper/69facb4cc0f56ed84308a641>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-09T05:00:04.795Z

Authors: Dutao Zhang, Tian Liao

Published: 2026-05-05T17:10:25.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Information Retrieval on BeIR Mixed (NQ, HotpotQA, SciFact)](<https://www.sota2.com/research/sota/information-retrieval-on-beir-mixed-nq-hotpotqa-scifact.md>): Information Retrieval; BeIR Mixed (NQ, HotpotQA, SciFact); Recall@10: 94.28.

- [Information Retrieval on BEIR (NQ, HotpotQA, SciFact subset)](<https://www.sota2.com/research/sota/information-retrieval-on-beir-nq-hotpotqa-scifact-subset.md>): Information Retrieval; BeIR nq, hotpotqa, scifact (mixed workload); Recall@10: 94.28.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.03989>)

[PDF](<https://arxiv.org/pdf/2605.03989.pdf>)
