Experimental Comparison of Agentic and Enhanced RAG
Apr 14, 2026
This episode explores a 2026 paper that experimentally compares three retrieval-augmented generation designs—naïve RAG, enhanced fixed pipelines, and agentic RAG—to ask when hand-engineered systems outperform LLM-driven tool-using agents. It breaks down core RAG concepts like routing, query rewriting, and reranking, and explains how agentic systems shift procedural control into the model at the cost of more latency, token use, and operational complexity. The discussion argues that many claims about “agentic” systems are inflated by weak baselines, and stresses that the real comparison should account for intermediate approaches such as corrective and self-reflective RAG. Listeners would find it interesting for its practical framework for deciding whether extra autonomy actually improves retrieval quality or just adds expense and hype.
Interactive Visualization: Experimental Comparison of Agentic and Enhanced RAG
Sources:
1. Is Agentic RAG worth it? An experimental comparison of RAG approaches — Pietro Ferrazzi, Milica Cvjeticanin, Alessio Piraccini, Davide Giannuzzi, 2026
http://arxiv.org/abs/2601.07711
2. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks — Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Kuttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela, 2020
https://scholar.google.com/scholar?q=Retrieval-Augmented+Generation+for+Knowledge-Intensive+NLP+Tasks
3. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection — Akari Asai, Zequn Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi, 2023
https://scholar.google.com/scholar?q=Self-RAG%3A+Learning+to+Retrieve%2C+Generate%2C+and+Critique+through+Self-Reflection
4. Corrective Retrieval Augmented Generation — Fenda Shi, Xilun Chen, Yizhou Sun, Hongxia Yang, 2024
https://scholar.google.com/scholar?q=Corrective+Retrieval+Augmented+Generation
5. A Survey on Retrieval-Augmented Text Generation for Large Language Models — Zhihan Gao, Chongyang Tao, Shuyan Qi, et al., 2024
https://scholar.google.com/scholar?q=A+Survey+on+Retrieval-Augmented+Text+Generation+for+Large+Language+Models
6. HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels — Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie Callan, 2023
https://scholar.google.com/scholar?q=HyDE%3A+Precise+Zero-Shot+Dense+Retrieval+without+Relevance+Labels
7. ReAct: Synergizing Reasoning and Acting in Language Models — Shunyu Yao, Jeffrey Zhao, Dian Yu, et al., 2023
https://scholar.google.com/scholar?q=ReAct%3A+Synergizing+Reasoning+and+Acting+in+Language+Models
8. Toolformer: Language Models Can Teach Themselves to Use Tools — Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, et al., 2023
https://scholar.google.com/scholar?q=Toolformer%3A+Language+Models+Can+Teach+Themselves+to+Use+Tools
9. Dense Passage Retrieval for Open-Domain Question Answering — Vladimir Karpukhin, Barlas Oğuz, Sewon Min, et al., 2020
https://scholar.google.com/scholar?q=Dense+Passage+Retrieval+for+Open-Domain+Question+Answering
10. Lost in the Middle: How Language Models Use Long Contexts — Nelson F. Liu, Kevin Lin, John Hewitt, et al., 2024
https://scholar.google.com/scholar?q=Lost+in+the+Middle%3A+How+Language+Models+Use+Long+Contexts
11. TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=TeaRAG%3A+A+Token-Efficient+Agentic+Retrieval-Augmented+Generation+Framework
12. SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=SLO-Conditioned+Action+Routing+for+Retrieval-Augmented+Generation%3A+Objective+Ablation+and+Failure+Modes
13. Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long Context Selection — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=Route+Before+Retrieve%3A+Activating+Latent+Routing+Abilities+of+LLMs+for+RAG+vs.+Long+Context+Selection
14. Applied Domain Adaptation of LLM-based Document Embeddings for Engineering Knowledge Retrieval — approx. recent engineering IR authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=Applied+Domain+Adaptation+of+LLM-based+Document+Embeddings+for+Engineering+Knowledge+Retrieval
15. From Retrieval to Response: Tracing the Impact of Embedding Quality in RAG Systems — approx. recent authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=From+Retrieval+to+Response%3A+Tracing+the+Impact+of+Embedding+Quality+in+RAG+Systems
16. AI Post Transformers: ComoRAG: Cognitively Inspired Narrative Reasoning — Hal Turing & Dr. Ada Shannon, 2025
https://podcast.do-not-panic.com/episodes/comorag-cognitively-inspired-narrative-reasoning/
17. AI Post Transformers: From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-03-22-from-prefix-cache-to-fusion-rag-9c5d39.mp3
18. AI Post Transformers: Real Context Size and Context Rot — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-07-real-context-size-and-context-rot-56cbb4.mp3
19. AI Post Transformers: AI Agent Traps and Prompt Injection — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-02-ai-agent-traps-and-prompt-injection-7ce4ba.mp3
Interactive Visualization: Experimental Comparison of Agentic and Enhanced RAG
1. Is Agentic RAG worth it? An experimental comparison of RAG approaches — Pietro Ferrazzi, Milica Cvjeticanin, Alessio Piraccini, Davide Giannuzzi, 2026
http://arxiv.org/abs/2601.07711
2. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks — Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Kuttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela, 2020
https://scholar.google.com/scholar?q=Retrieval-Augmented+Generation+for+Knowledge-Intensive+NLP+Tasks
3. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection — Akari Asai, Zequn Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi, 2023
https://scholar.google.com/scholar?q=Self-RAG%3A+Learning+to+Retrieve%2C+Generate%2C+and+Critique+through+Self-Reflection
4. Corrective Retrieval Augmented Generation — Fenda Shi, Xilun Chen, Yizhou Sun, Hongxia Yang, 2024
https://scholar.google.com/scholar?q=Corrective+Retrieval+Augmented+Generation
5. A Survey on Retrieval-Augmented Text Generation for Large Language Models — Zhihan Gao, Chongyang Tao, Shuyan Qi, et al., 2024
https://scholar.google.com/scholar?q=A+Survey+on+Retrieval-Augmented+Text+Generation+for+Large+Language+Models
6. HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels — Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie Callan, 2023
https://scholar.google.com/scholar?q=HyDE%3A+Precise+Zero-Shot+Dense+Retrieval+without+Relevance+Labels
7. ReAct: Synergizing Reasoning and Acting in Language Models — Shunyu Yao, Jeffrey Zhao, Dian Yu, et al., 2023
https://scholar.google.com/scholar?q=ReAct%3A+Synergizing+Reasoning+and+Acting+in+Language+Models
8. Toolformer: Language Models Can Teach Themselves to Use Tools — Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, et al., 2023
https://scholar.google.com/scholar?q=Toolformer%3A+Language+Models+Can+Teach+Themselves+to+Use+Tools
9. Dense Passage Retrieval for Open-Domain Question Answering — Vladimir Karpukhin, Barlas Oğuz, Sewon Min, et al., 2020
https://scholar.google.com/scholar?q=Dense+Passage+Retrieval+for+Open-Domain+Question+Answering
10. Lost in the Middle: How Language Models Use Long Contexts — Nelson F. Liu, Kevin Lin, John Hewitt, et al., 2024
https://scholar.google.com/scholar?q=Lost+in+the+Middle%3A+How+Language+Models+Use+Long+Contexts
11. TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=TeaRAG%3A+A+Token-Efficient+Agentic+Retrieval-Augmented+Generation+Framework
12. SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=SLO-Conditioned+Action+Routing+for+Retrieval-Augmented+Generation%3A+Objective+Ablation+and+Failure+Modes
13. Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long Context Selection — approx. recent arXiv authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=Route+Before+Retrieve%3A+Activating+Latent+Routing+Abilities+of+LLMs+for+RAG+vs.+Long+Context+Selection
14. Applied Domain Adaptation of LLM-based Document Embeddings for Engineering Knowledge Retrieval — approx. recent engineering IR authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=Applied+Domain+Adaptation+of+LLM-based+Document+Embeddings+for+Engineering+Knowledge+Retrieval
15. From Retrieval to Response: Tracing the Impact of Embedding Quality in RAG Systems — approx. recent authors unknown from snippet, 2024/2025
https://scholar.google.com/scholar?q=From+Retrieval+to+Response%3A+Tracing+the+Impact+of+Embedding+Quality+in+RAG+Systems
16. AI Post Transformers: ComoRAG: Cognitively Inspired Narrative Reasoning — Hal Turing & Dr. Ada Shannon, 2025
https://podcast.do-not-panic.com/episodes/comorag-cognitively-inspired-narrative-reasoning/
17. AI Post Transformers: From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-03-22-from-prefix-cache-to-fusion-rag-9c5d39.mp3
18. AI Post Transformers: Real Context Size and Context Rot — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-07-real-context-size-and-context-rot-56cbb4.mp3
19. AI Post Transformers: AI Agent Traps and Prompt Injection — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-02-ai-agent-traps-and-prompt-injection-7ce4ba.mp3
Interactive Visualization: Experimental Comparison of Agentic and Enhanced RAG