mlsanityData to 14 Oct 2026

Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG

arXiv 2507.10411 ↗First posted 14 Jul 2025cs.IRcited by 5

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 2 more
Abstract (arXiv)

Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by recent research works such as Search-R1, enables the model to decide when to search and obtain external information. However, the queries generated by such Agentic RAG models and the role of the retriever in obtaining high-quality answers remain understudied. To this end, this initial study examines the applicability of query performance prediction (QPP) within the recent Agentic RAG models Search-R1 and R1-Searcher. We find that applying effective retrievers can achieve higher answer quality within a shorter reasoning process. Moreover, the QPP estimates of the generated queries, used as an approximation of their retrieval quality, are positively correlated with the quality of the final answer. Ultimately, our work is a step towards adaptive retrieval within Agentic RAG, where QPP is used to inform the model if the retrieved results are likely to be useful.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 49 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

21 of 49 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  2. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systems26 Jul
  3. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation8 Mar
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  8. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  9. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  10. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  11. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  12. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 138
4 more
  1. 2023Query Performance Prediction: From Ad-hoc to Conversational Searchcited by 16
  2. 2025KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generationcited by 13
  3. 2025Is Relevance Propagated from Retriever to Generator in RAG?cited by 11
  4. 2025Constructing and Evaluating Declarative RAG Pipelines in PyTerriercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generationcited by 2
  2. 2026RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesiscited by 1
  3. 2026A Picture of Agentic Searchcited by 1
  4. 2026Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelinescited by 1
  5. 2026Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  2. 2026Is Agentic RAG worth it? An experimental comparison of RAG approaches
  3. 2026Agentic-R: Learning to Retrieve for Agentic Search
  4. 2025QAgent: A modular Search Agent with Interactive Query Understanding
  5. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  6. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  7. 2026Test-Time Strategies for More Efficient and Accurate Agentic RAG
  8. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges