Index of everything on this site: https://ai.hiina.space/index.md
What exists. BrowseComp-Plus is the template: a frozen 100,195-document corpus, 830 queries, gold documents, mined hard negatives, an oracle condition and search-call counts. Its retriever-only swing of 2x or more on a fixed corpus is exactly the effect size you want to look for, but it varies the retriever, not the site (arXiv). WebWalkerQA has agents traverse real sites (best about 37.5%, falling with depth) (ACL). Needle in the Web grades difficulty by claim centrality and finds agents at 30% to 33% versus humans at 79% to 86%, with cluttered sites worse (arXiv). The Synthetic Web Benchmark builds miniature internets; one misleading top-ranked article cut GPT-5 from 65.1% to 18.2% (arXiv). Live-web numbers drift: an audit measured Operator's self-reported 87% on WebVoyager at 68.6% (arXiv), and BrowseComp is near saturation on self-reports (BenchLM).
The real gap. Practitioner tools check delivery, not task success. Agent Reading Test plants canary tokens to catch truncation, JS-only content and HTML/Markdown divergence, and caught agents misreporting their own scores (Carey). The 22-check afdocs score's author says its link to task completion is unmeasured; one site scored 100 there and 33 on another checker (Carey). GEO, the closest "SEO for agents", measures which source a generator credits (up to 41% gains from citing sources and adding statistics, in a GPT-3.5-era pipeline), not whether an agent finds a fact (arXiv). No study I found renders one corpus several ways and crosses it with several agents; with about five search wordings tried, call it probably unoccupied.
A cheap design that separates model navigation from site
navigability. Generate about 1,000 pages of invented entities
in the style of agent-written working notes, so answers cannot come from
memory. Plant 60 facts at link depths 1 to 4 (half single-hop, half
two-page), grade difficulty by claim centrality, add a conflicting
near-duplicate per fact and one adversarial top-ranked page. Render the
tree as a JS app, server HTML, .md plus index,
.md plus index plus /search, git repo,
corpus.db and MCP. Run a fetch-only API loop, Claude Code,
Codex CLI, Gemini CLI and one open-weight model, three runs per valid
cell, with closed-book and oracle controls. Grade by exact match and
take efficiency from server logs, not self-reports: hops to first gold
page, bytes, tool calls, tokens.
Fit accuracy as agent + format + agent×format. The format effect is site navigability, the agent effect is model navigation skill, and the interaction says which affordances each agent class needs. The cleanest per-site number is navigability loss: oracle accuracy minus accuracy under that format for a fixed agent. Released as a harness, this would be the first navigability score validated against task completion.
Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space