Agents can reason. What they lack is a substrate to reason over: full paper text, real citations, and a retrieval loop that doesn't hand back ten blue links. Ask a question, get an answer grounded in sources you can verify.
Web search was built to hand a human ten links. Give that to an agent and it does what you'd do — badly, expensively, and without a citation you can check.
[arXiv:2512.15176] maps to a real paper. It says "no relevant papers" rather than inventing one.--web for pricing, products and news, from cached page bodies.A question goes in; the service picks its own tools, reads sources when it needs to, and streams back a cited answer. The arXiv side reads paper sections; the web side reads cached page bodies.
Qdrant hybrid retrieval over a local full-text corpus, plus the paper bodies themselves.
Answers with real IDs — [arXiv:2512.15176].
Best for — methods, reported numbers, experimental results, comparing what two papers claim on the same benchmark.
Google plus cached page bodies. Answers with links to real URLs, and marks which pages were read in full versus snippet-only.
Best for — current events, products, pricing, anything that was never going to be in a paper.
| Effort | Gather rounds | First token · arXiv | First token · web | Reach for it when |
|---|---|---|---|---|
default | 1–2 | 3–4s | 5–9s | You want an answer now |
high | 3 | 7–8s | ≈13s | Comparing across papers |
xhigh | 4–5 | 9–13s | longer | Survey-shaped questions |
Rounds are a ceiling, not a floor — it converges early once the evidence is enough. Raising effort adds reading rounds but can't redirect first-round recall; if an answer misses, rephrase more specifically instead.
An agent deciding whether a paper is worth reading shouldn't pay for the whole paper. Each
layer is a separate call, cheap enough to run across a full candidate set. Real numbers, from
2409.05591.
Judging whether this paper is worth reading costs 300 tokens, not 23,311 — 78× less. A question about its method costs 5,919. Search, judge, then read.
Author, organisation, category, venue (NeurIPS ↔ NIPS aliases resolve), venue year, date ranges, minimum citations, offset paging, opt-in fine reranking.
What's actually being read right now — deepxiv trending for the rolling window, --popularity for a single paper's views, tweets and likes.
PubMed Central, bioRxiv and medRxiv share the same reading verbs. Open-access only — agents work on unrestricted data instead of hitting paywalls.
An agent handed a bare ask(query) tool
will use this API poorly. These three distinctions belong in your tool descriptions.
Never invents an arXiv ID or URL — it says no relevant papers rather than fabricate one. Tell your agent to preserve them in what it reports back.
A ten-paper retrieval often supports one citation. sources is the retrieval set — filter to IDs that appear in the answer, or your agent will present unrelated papers as evidence.
Hit max_answer_tokens and the API sets answer_truncated. Surface it, or an agent will summarise a cut-off answer as though it were whole.
On the web backend evidence has two strengths: pages marked read were parsed in full, the rest gave only a search snippet. It never fetches live — an uncached page is weaker evidence.
Not a crawl of abstract pages. Parsed full text, sectioned, embedded, re-synced daily.
| Source | Scale | Depth | Freshness |
|---|---|---|---|
| arXiv | 3,127,076 papers | Full text, sectioned, hybrid-indexed | T+0 — same day as announcement |
| PubMed Central | ~7.5M articles | Structured parse, section access | Daily |
| bioRxiv / medRxiv | Preprint corpus | Section access, same reading verbs | Daily |
| Open web | Google index | Cached page bodies, not live fetch | Cache-first |
Agentic calls don't consume your general limit, and vice versa. Agentic search needs a
registered key — the SDK's auto-registered token isn't
eligible and returns 403.
| Key | General requests / day | Agentic calls / day | How to get it |
|---|---|---|---|
| Auto-registered | 1,000 | — not eligible | Automatic on first CLI use |
| Registered | 10,000 | 30, free | data.rag.ac.cn/signup → |
| Lite / Premium | Custom | 500 / 10,000 | Email tommy[at]chien.io with your use case |
Lost your key? Sign in — your keys are on your dashboard.
Free test papers, no token needed — arXiv 2409.05591, 2504.21776; PMC PMC544940.
CLI, the Reader client, and a token that registers itself on first use.
Google sign-in or phone verification. Under a minute, and lifts you to 10,000 requests plus 30 agentic calls a day.
Be specific — "what speedup does X report on HumanEval" beats "speculative decoding" by a wide margin. Chinese works directly.
Free to start. 3.1M full-text papers, real citations, an answer in under four seconds.