Equation 27 · Naive, Graph, and Agentic: A Systems Comparison of RAG Architectures
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol k
k is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
Both approaches share the same engineering consequence: the number of retrieval-generation rounds, call it k , is no longer fixed at one. Latency and cost scale with k , and unlike the naive or hybrid families, k is now a property of the question rather than of the architecture — a single-hop question still costs roughly one round, but a four-hop question costs roughly four, and the system pays that multiplier whether or not the caller anticipated it. IRCoT bounds this in practice by capping the number of reasoning steps and by using retrieval and reasoning specifically tuned for the multi-hop benchmarks it was evaluated on; FLARE bounds it by triggering additional retrieval only on measured…
Read the full surrounding passage
Both approaches share the same engineering consequence: the number of retrieval-generation rounds, call it k , is no longer fixed at one. Latency and cost scale with k , and unlike the naive or hybrid families, k is now a property of the question rather than of the architecture — a single-hop question still costs roughly one round, but a four-hop question costs roughly four, and the system pays that multiplier whether or not the caller anticipated it. IRCoT bounds this in practice by capping the number of reasoning steps and by using retrieval and reasoning specifically tuned for the multi-hop benchmarks it was evaluated on; FLARE bounds it by triggering additional retrieval only on measured low confidence rather than at every step, which keeps the multiplier close to one on easy inputs and lets it grow on hard ones. Neither of these figures — the reported point gains on multi-hop QA benchmarks — is comparable to GraphRAG’s comprehensiveness gains on corpus summarisation or to Self-RAG’s citation-accuracy figures discussed next; they were measured on different tasks built to expose different failures, and citing one as evidence against another would be a category error, not a finding.
Sources cited in the article section
- [7] Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions ↗
- [8] Active Retrieval Augmented Generation ↗
These citations give research context. Read each source to check which claims it supports.
Return to Naive, Graph, and Agentic: A Systems Comparison of RAG Architectures