{"uid":"cap_m9Bha66EP0aZPkC3tRT27","slug":"lumen-arxiv-preprint-search-abb7a61d","name":"Lumen arXiv Preprint Search","description":"Search arXiv preprints: id, title, abstract, authors, categories, dates, PDF link. Supports arXiv field prefixes (ti:, au:, cat:). {query, limit<=50, sort:relevance|date}.","url":"https://lumenworks-x402-decoder.onrender.com/v1/arxiv/search?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":null,"responseSchema":{"type":"json","example":{"query":"LLM agents tool use","total":1585251,"source":"arXiv API","results":[{"id":"2111.01762v1","pdf":"https://arxiv.org/pdf/2111.01762v1","url":"http://arxiv.org/abs/2111.01762v1","title":"AIRCC-Clim: a user-friendly tool for generating regional probabilistic climate change scenarios and risk measures","authors":["Francisco Estrada","Oscar Calderón-Bustamante","Wouter Botzen"],"summary":"Complex physical models are the most advanced tools available for producing realistic simulations of the climate system. However, such levels of realism imply high computational cost and restrictions on their use for policymaking and risk assessment. Two central characteristics of climate change are uncertainty and that it is a dynamic problem in which international actions can significantly alter…","updated":"2021-10-30T11:09:03Z","published":"2021-10-30T11:09:03Z","categories":["physics.ao-ph","econ.GN","stat.AP"]},{"id":"2605.18805v1","pdf":"https://arxiv.org/pdf/2605.18805v1","url":"http://arxiv.org/abs/2605.18805v1","title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","authors":["Imad Aouali","Flavian Vasile","Otmane Sakhi"],"summary":"LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and…","updated":"2026-05-11T18:55:32Z","published":"2026-05-11T18:55:32Z","categories":["cs.IR","cs.AI","cs.LG"]}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ENR95C-UUTL-YSjV03m2L","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Search arXiv preprints by query with full metadata including id, title, abstract, authors, categories, dates, and PDF link","exampleAgentPrompt":"Search arXiv for the latest papers on LLM agents and tool use — give me up to 10 results sorted by date.","exampleUseCases":[{"title":"Finding recent ML papers by topic","prompt":"Find me the 20 most recent arXiv papers on diffusion models for image synthesis, sorted by date."},{"title":"Author publication lookup","prompt":"Search arXiv for all papers authored by Yann LeCun — give me up to 15 results sorted by relevance."},{"title":"Category-specific research survey","prompt":"Pull up to 50 arXiv preprints from the cs.AI category about reinforcement learning from human feedback, sorted by relevance."}],"resultDescription":"A JSON object containing the original query, total result count, source label, and an array of matching papers. Each paper includes its arXiv id, canonical URL, PDF URL, title, authors list, summary/abstract, published date, updated date, and subject categories.","failureModes":["Query returns zero results if the search terms are too specific or use unsupported syntax","Exceeding the limit of 50 results per call is rejected","Invalid arXiv field prefixes may cause unexpected results or empty response","Service unavailable if the underlying arXiv API is down or rate-limiting","Malformed request body returns an HTTP error without result data"],"whenToPreferThis":"Use this endpoint when you need structured metadata from arXiv preprints — especially when you need authors, categories, and PDF links in a single call and want to filter using arXiv field prefixes (ti:, au:, cat:). Prefer this over direct arXiv API access when operating in an x402-payment context or when you need a clean JSON response without parsing arXiv's Atom XML feed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:43:06.123Z","isFirstParty":false,"canonicalSlug":"lumen-arxiv-preprint-search-abb7a61d"}