Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
智能體檢索透過 ReAct 智能體迴圈,結合大語言模型的推理能力與檢索器探索語料的效率,以應付複雜檢索任務。使用相同嵌入模型時,它較標準檢索的 nDCG@10 高 8.7 分,並在 ViDoRe v3 和 BRIGHT 排行榜取得具競爭力的結果。代價是每次查詢平均需時 107.4 秒,消耗 764.1K 個輸入 token 和 5.8K 個輸出 token;標準檢索平均需時 0.67 秒。
Published on Oct 5
Authors:
,
,
,
,
,
,
,
,
,
Abstract
Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstructured data. However, dense retrieval relies on surface-level semantic similarity, which is insufficient for increasingly complex search applications. Here, we investigate agentic retrieval that combines the reasoning capabilities of Large Language Models (LLMs) with the efficient corpus exploration of retrievers in a ReAct agentic loop to solve complex retrieval tasks. In our experiments, we show that agentic retrieval is more effective than standard retrieval, improving nDCG@10 by 8.7 points using the same embedding model. Moreover, while specialized retrieval methods struggle on out-of-domain tasks, agentic retrieval is highly generalizable: the same pipeline achieves competitive results on both the ViDoRe v3 and BRIGHT leaderboards. However, this improvement comes at a cost. On average, agentic retrieval takes 107.4 seconds, compared to 0.67 seconds for standard retrieval, and consumes 764.1K input and 5.8K output tokens per query. In short, our study demonstrates the effectiveness of agentic retrieval in modern data systems and motivates future work on more cost-efficient retrieval agents for large-scale deployment.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.05750
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.05750 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.05750 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.05750 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co