Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.14337 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918161699307520 |
|---|---|
| author | Park, Jaewan Cho, Solbee Lee, Jay-Yoon |
| author_facet | Park, Jaewan Cho, Solbee Lee, Jay-Yoon |
| contents | Iterative retrieval-augmented generation (RAG) enables large language models to answer complex multi-hop questions, but each additional loop increases latency, costs, and the risk of introducing distracting evidence, motivating the need for an efficient stopping strategy. Existing methods either use a predetermined number of iterations or rely on confidence proxies that poorly reflect whether more retrieval will actually help. We cast iterative RAG as a finite-horizon Markov decision process and introduce Stop-RAG, a value-based controller that adaptively decides when to stop retrieving. Trained with full-width forward-view Q($λ$) targets from complete trajectories, Stop-RAG learns effective stopping policies while remaining compatible with black-box APIs and existing pipelines. On multi-hop question-answering benchmarks, Stop-RAG consistently outperforms both fixed-iteration baselines and prompting-based stopping with LLMs. These results highlight adaptive stopping as a key missing component in current agentic systems, and demonstrate that value-based control can improve the accuracy of RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stop-RAG: Value-Based Retrieval Control for Iterative RAG Park, Jaewan Cho, Solbee Lee, Jay-Yoon Machine Learning Artificial Intelligence Iterative retrieval-augmented generation (RAG) enables large language models to answer complex multi-hop questions, but each additional loop increases latency, costs, and the risk of introducing distracting evidence, motivating the need for an efficient stopping strategy. Existing methods either use a predetermined number of iterations or rely on confidence proxies that poorly reflect whether more retrieval will actually help. We cast iterative RAG as a finite-horizon Markov decision process and introduce Stop-RAG, a value-based controller that adaptively decides when to stop retrieving. Trained with full-width forward-view Q($λ$) targets from complete trajectories, Stop-RAG learns effective stopping policies while remaining compatible with black-box APIs and existing pipelines. On multi-hop question-answering benchmarks, Stop-RAG consistently outperforms both fixed-iteration baselines and prompting-based stopping with LLMs. These results highlight adaptive stopping as a key missing component in current agentic systems, and demonstrate that value-based control can improve the accuracy of RAG systems. |
| title | Stop-RAG: Value-Based Retrieval Control for Iterative RAG |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.14337 |