What this means
Decomposing a user question into multiple related searches or subqueries.
Historical record
Google Search upgrades AI Mode with Gemini 4 Hydrogen
A change in how Google AI Search handles complex queries and retrieves links is material to observing source exposure and citation patterns over time.
Sequential-decision research shows search policy and retriever jointly shape evidence exposure
AI agents may expose or miss relevant evidence depending on query-branch decisions and allocation of attention across ranked lists, not just the rank of a webpage for a single query.
ACARe research shows task context can improve reranking of agent-generated search queries
Query fan-out alone may not explain which documents are selected for agentic answers. Context-aware reranking adds a distinct source-selection stage that visibility measurement and retrieval experiments should account for.
OpenAI details agentic retrieval, ranking and auction architecture for ChatGPT Ads
Paid conversational discoverability depends on opportunity detection, semantic retrieval, eligibility, auction and frontend display, each distinct from organic source citation and brand mention. Measurement needs separate funnel stages.
How AI agents search: Peer-reviewed ASQ study maps agent query reformulation and retrieval workload
AI agents can issue numerous evolving retrieval queries for a single user information need. Measuring only the initial query can miss intermediary source exposure and retrieval workload. This evidence supports treating query fan-out, retrieved source exposure, and final citations as separate stages.
OpenDS-World benchmarks evidence discovery by agents in live web environments
AI discovery depends on whether agents can find, navigate and interpret source material before deciding what to cite or use in an answer.
Controlled research finds location channels change AI citations and business recommendations
AI visibility and GEO audits that use a single geographic origin can mischaracterize brand and source exposure. Declared location, network country and run-to-run variation need to be recorded as separate measurement variables.
Glasseek research introduces auditable deep-search agent evaluation
Agentic search benchmarks can overstate retrieval capability if an agent encounters hidden answer keys or benchmark data while searching. The work highlights why evidence provenance, search trajectories and benchmark leakage must be audited before drawing conclusions about AI discovery.
Research traces ChatGPT Web retrieval-to-citation behavior across model settings
AI citation measurement cannot reliably infer all cited URLs from Google Search or API proxy results alone. Repeated sampling and separating retrieval from citation outcomes across model settings may improve GEO measurement validity.
Research separates retrieval, content matching and model knowledge in AI citations
AI visibility measurement should distinguish retrieval eligibility and generated subqueries from answer citation and brand mentions; formatting-only interventions cannot be assumed to change selection.
SEEDS research separates retrieved candidates from evidence admitted into agent reasoning
An AI agent may retrieve a page yet never admit its full content into the reasoning context. AI discovery and citation measurement should distinguish retrieval exposure, preview inspection, evidence admission and final answer citations.
IndexAct research separates candidate-set refinement from text inspection in agentic search
Agentic discovery can depend on how an agent narrows candidate sources and when it chooses to inspect evidence, not only on which documents a search index initially matches.
Agentic retrieval study quantifies quality gains alongside steep latency and token costs
Source discovery in multi-step agents can differ from a single semantic similarity ranking, but additional query fan-out and reasoning impose material latency and cost. Evaluation of AI discovery pipelines should track evidence quality and search budget together.
Programmatic Search Agents demonstrate that evidence presentation matters beyond query reformulation
For AI discovery, a page entering retrieval is not equivalent to its supporting passage reaching the model or being used in an answer. The research supports separating retrieval, evidence delivery and final source use in visibility and attribution measurement.
T-Search research separates multi-step evidence retrieval from answer generation
AI discovery has an upstream evidence-retrieval stage distinct from final citation selection. Multi-round searches and alternative retrieval rollouts can change which source chunks are available to a generator; citation monitoring alone does not measure this upstream coverage.
INSPIRE benchmark measures exposure, selection and ranking losses in research agents
A source that an agent never retrieves cannot be cited, and retrieved evidence can still be omitted or poorly ranked. Citation visibility measurement should distinguish these failure stages.
Research characterizes cross-platform conversational web search behavior
The results provide empirical evidence that AI discovery is a multi-stage process: deciding to search, formulating machine-written queries, retrieving candidate sources, selecting evidence, grounding responses, and exposing citations can vary independently across platforms.
Google Research demonstrates property-aligned query fan-out with Retrieve-for-Train
It provides primary research evidence that AI retrieval can depend on complementary semantic coverage across a fan-out, rather than only matching a single canonical query, and gives Visibility OS a measurable framework for thinking about fan-out quality.
Perplexity introduces Q2D-Web for large-scale retrieval evaluation in agentic RAG
The visible user prompt is not necessarily the query a source competes for. AI visibility therefore depends on several distinct stages: query reformulation, first-stage retrieval, ranking, evidence selection, and eventual citation.
ITER uses prior agent search history to improve iterative evidence retrieval
Multi-step agentic discovery is path-dependent: the same current subquery can be evaluated in light of earlier questions and visited evidence. Source visibility measurement should consider complete search trajectories.
Breadcrumbing study shows adaptive search-result injection can steer multi-step agent evidence chains
Agentic retrieval and source selection can be influenced over multiple search steps, so corroboration among search results does not automatically establish independence when an intermediary can alter the observation stream.
SIEVE demonstrates structure-aware search, inspection and section-level fetching for research agents
Agentic discovery may depend on which parts of a source can be addressed and fetched, not just whether the page appears in a search index. Structured document access affects retrieval precision and context efficiency in the tested system.
EMBL AI Librarian demonstrates multi-query evidence retrieval in scientific research agents
This provides direct research evidence for separating multi-query retrieval, source selection and passage-level evidence grounding when analyzing AI discovery pipelines; it does not measure public-web publisher visibility.
RISE research tests bounded, navigable evidence workspaces for agentic search
For AI discovery research, the experiment distinguishes document candidate inclusion, access to evidence inside a retrieved document, and final answer generation. It demonstrates that evidence-delivery interfaces can influence agent effectiveness and cost in controlled tasks.
Deep literature search study separates citation coverage from topical relevance
AI discovery measurement should separate whether sources were found from how they were ranked and judged relevant; existing human citations are not a complete or unambiguous ground truth for evaluating retrieval.
Research shows repeated UGC retrieval can contaminate deep-research citations
Multi-query agentic retrieval can repeatedly select the same editable sources. Citation occurrence alone is not evidence of factual reliability; provenance, moderation and source integrity affect trustworthy AI discovery.
Google publishes official guidance for generative AI Search visibility
Practitioners gained first-party guidance separating verified requirements from speculative AEO/GEO tactics.
SIRA demonstrates corpus-aware one-shot retrieval as an alternative to repeated agent search
Agentic source discovery does not necessarily require more query fan-out. Discriminative vocabulary and corpus-aware retrieval controls may change the efficiency and source-selection behavior of future retrieval-augmented systems.
Google adds source-exploration links, subscription labels and community previews to AI Search
The visibility of a publisher source in an AI answer can involve link placement, labels and previews rather than simply whether a URL is cited; these display distinctions matter for measurement.
CoSearch jointly trains agent reasoning and evidence ranking for multi-step search
Intermediate agent-generated subqueries and the document admission/reranking stage can shape which evidence reaches a reasoning agent. This suggests retrieval and reranking should be evaluated separately from final citations.
MERRIN benchmark exposes multimodal evidence-selection and over-search failures in web agents
Multimodal AI discoverability requires that agents retrieve and correctly interpret the right source modality, not merely find a webpage. More query fan-out can introduce distracting evidence and impair final grounding.
LRAT trains search retrievers on agent browsing and reasoning trajectories
Documents that help an agent resolve an intermediate information gap may differ from those most relevant to the initial user query; retriever training can therefore change which sources are surfaced to AI agents.
MC-Search benchmark measures stepwise multimodal retrieval and agent planning
Visual and agentic AI discovery can require multiple dependent searches across text and images. Measurement of evidence discovery needs hop-level and modality-aware diagnostics, not just final-answer accuracy.
SAGE benchmark finds agent query wording changes retrieval effectiveness
Which sources enter an AI agent's evidence pool depends on its intermediate query formulations and retrieval configuration; semantic similarity alone does not predict exposure across tasks.
Large-scale agentic search logs reveal cross-step evidence reuse and intent-dependent query trajectories
Agentic discovery involves sequences of queries informed by prior retrieval, so measurement limited to the initial prompt or a single cited result can miss how sources enter later searches.
Agentic-R trains retrievers for multi-step search using local relevance and final-answer utility
In multi-step AI discovery, passages selected for semantic similarity to a subquery may not help complete the final answer. Retriever training objectives can therefore change which evidence reaches an agent, independently of traditional search ranking or publisher content changes.
Google expands AI Mode and Deep Search using query fan-out
Topical completeness, subtopic relevance and retrieval across multiple intents become central to AI search visibility.
Google introduces AI Mode and describes query fan-out
Visibility is no longer tied only to the user’s literal query; sources can be discovered through hidden subqueries and related retrieval paths.